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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     viewpoints
    -0.07
     explicitly
    -0.07
    .params
    -0.07
    .CONNECT
    -0.06
     Louisville
    -0.06
    (amount
    -0.06
    irt
    -0.06
    Adapter
    -0.06
    .helpers
    -0.06
     weddings
    -0.06
    POSITIVE LOGITS
     مکان
    0.07
    SRC
    0.07
    哦
    0.06
    に行
    0.06
     Stunden
    0.06
    _pri
    0.06
    rezent
    0.06
    _students
    0.06
     ček
    0.06
    backs
    0.06
    Act Density 0.078%

    No Known Activations