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

    Neuronpedia

    INDEX
    Explanations

    biz

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    וצרים
    -0.08
    .Criteria
    -0.07
    .lastIndexOf
    -0.07
    oes
    -0.07
    .moveToFirst
    -0.07
    yl
    -0.07
    Path
    -0.07
     sổ
    -0.07
    (AF
    -0.07
     SOS
    -0.07
    POSITIVE LOGITS
     tangled
    0.07
    蜘蛛
    0.07
    髋
    0.07
     cuckold
    0.07
     �
    0.07
    Door
    0.06
     arresting
    0.06
     Alarm
    0.06
     knitting
    0.06
     Verb
    0.06
    Act Density 0.000%

    No Known Activations