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

    Neuronpedia

    INDEX
    Explanations

    Incomplete sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TableWidgetItem
    -0.07
     몇
    -0.07
    旧
    -0.06
     Belize
    -0.06
    間
    -0.06
     BP
    -0.06
    �
    -0.06
    İZ
    -0.06
     😉
    -0.06
     REPRESENT
    -0.06
    POSITIVE LOGITS
    .Restrict
    0.09
    _hi
    0.07
    _guess
    0.06
     الل
    0.06
     [...]
    0.06
    scheduled
    0.06
    .getToken
    0.06
    adığı
    0.06
    _padding
    0.06
     PST
    0.06
    Act Density 0.071%

    No Known Activations