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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    咳
    -0.06
    妖
    -0.06
    杀人
    -0.06
     hele
    -0.06
    千万别
    -0.06
     ignore
    -0.06
     anus
    -0.06
     fem
    -0.06
     underline
    -0.06
     gı
    -0.06
    POSITIVE LOGITS
    .Dispatcher
    0.08
     tax
    0.08
    _LAT
    0.07
     Treasurer
    0.07
     cable
    0.07
    bilt
    0.07
    原标题
    0.07
     CID
    0.07
    .getClass
    0.07
    $q
    0.06
    Act Density 0.007%

    No Known Activations