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

    Neuronpedia

    INDEX
    Explanations

    special characters

    np_max-act · gemini-2.0-flash

    This neuron detects past‐tense verbs ending in “-ed.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    :T
    -0.06
     edition
    -0.06
    dataType
    -0.06
    雲
    -0.06
    .getServer
    -0.06
    _elems
    -0.06
    (pc
    -0.06
    Unicode
    -0.06
    .staff
    -0.06
     měsí
    -0.06
    POSITIVE LOGITS
     nutritious
    0.07
    対
    0.07
    ENTIC
    0.07
     Exhaust
    0.07
     Prix
    0.06
    	git
    0.06
     Zucker
    0.06
    MouseClicked
    0.06
    ric
    0.06
    溶
    0.06
    Act Density 0.400%

    No Known Activations