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

    Neuronpedia

    INDEX
    Explanations

    Pro

    np_max-act · gemini-2.0-flash

    This neuron responds to floating-point numeric tokens (numbers with decimal points).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .normalize
    -0.07
    .lesson
    -0.07
     ±
    -0.06
    ола
    -0.06
    Listen
    -0.06
    OrderBy
    -0.06
    AutoresizingMask
    -0.06
     Listener
    -0.06
    .example
    -0.06
    Man
    -0.06
    POSITIVE LOGITS
     correspond
    0.06
     vowed
    0.06
    ấm
    0.06
     hospital
    0.06
    (graph
    0.06
    _SUITE
    0.06
     Hotel
    0.06
     inspired
    0.06
     initially
    0.06
    なた
    0.06
    Act Density 0.008%

    No Known Activations