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

    Neuronpedia

    INDEX
    Explanations

    legal/instructional discourse

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    |wx
    -0.08
     reacting
    -0.07
    _exceptions
    -0.07
    *num
    -0.07
     QDateTime
    -0.07
    ikip
    -0.07
    麻烦
    -0.07
    (http
    -0.07
    inions
    -0.07
     gone
    -0.07
    POSITIVE LOGITS
    (forKey
    0.08
    埃尔
    0.07
    𝐽
    0.07
     wooden
    0.07
    重重
    0.07
    :number
    0.07
    .sd
    0.07
    SET
    0.07
    .model
    0.06
     setIs
    0.06
    Act Density 0.218%

    No Known Activations