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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Expr
    -0.07
     सज
    -0.07
    ]',↵
    -0.07
     пацієн
    -0.07
     وس
    -0.06
     dest
    -0.06
    -roll
    -0.06
     зан
    -0.06
    <Cell
    -0.06
     exiting
    -0.06
    POSITIVE LOGITS
    jejer
    0.07
    rschein
    0.07
    216
    0.06
     Oliv
    0.06
     модели
    0.06
    ｉ
    0.06
     pohled
    0.06
     Santo
    0.06
     RJ
    0.06
    лер
    0.06
    Act Density 0.000%

    No Known Activations