Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    become

    np_max-act · gemini-2.0-flash

    technical descriptions of inventions related to apparatuses and devices.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects forward-reference phrases signaling that further details or advantages “will become apparent” (e.g., “will become apparent,” “will become clear”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    イス
    -0.07
     Celtics
    -0.06
    incer
    -0.06
     проч
    -0.06
     Liv
    -0.06
     Loading
    -0.06
    Su
    -0.06
    arters
    -0.06
    _brand
    -0.06
     řid
    -0.06
    POSITIVE LOGITS
    urally
    0.08
    formData
    0.07
    ural
    0.06
    �
    0.06
    (sqrt
    0.06
     calloc
    0.06
     mục
    0.06
    quired
    0.06
     {%
    0.06
    (engine
    0.06
    Act Density 0.001%

    No Known Activations