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

    Neuronpedia

    INDEX
    Explanations

    attribute mentions

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numeric tokens (numbers with decimal points).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (TimeSpan
    -0.06
    classnames
    -0.06
    upo
    -0.06
     Herman
    -0.06
    plets
    -0.06
    /*----------------------------------------------------------------------------
    -0.06
    ,this
    -0.06
    rows
    -0.06
    onsense
    -0.05
     pulmonary
    -0.05
    POSITIVE LOGITS
     Similarly
    0.07
    ницип
    0.07
    /csv
    0.07
     create
    0.07
     شدن
    0.07
     coment
    0.06
    _teacher
    0.06
     attractive
    0.06
    র
    0.06
    ¬
    0.06
    Act Density 0.001%

    No Known Activations