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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron never activates—it doesn’t respond to any tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	The
    -0.07
    _entities
    -0.07
    되지
    -0.07
    collections
    -0.07
    _bounds
    -0.06
    Coal
    -0.06
    (UI
    -0.06
     incur
    -0.06
    Day
    -0.06
    >You
    -0.06
    POSITIVE LOGITS
    δα
    0.07
    ."'";↵
    0.06
     φορ
    0.06
    FlatButton
    0.06
    .put
    0.06
     efter
    0.06
    jq
    0.06
    }")↵
    0.06
    _elim
    0.06
     Munich
    0.06
    Act Density 0.074%

    No Known Activations