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

    Neuronpedia

    INDEX
    Explanations

    politics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    よ
    -0.07
    Examples
    -0.07
     Buddhism
    -0.06
    E
    -0.06
    пе
    -0.06
    思
    -0.06
     dummy
    -0.06
    idis
    -0.06
     tys
    -0.06
    avis
    -0.06
    POSITIVE LOGITS
    .full
    0.07
     星
    0.06
     làm
    0.06
    .Msg
    0.06
    频次
    0.06
     přímo
    0.06
     culo
    0.06
     DIRECT
    0.06
    DIRECT
    0.06
    ELEMENT
    0.06
    Act Density 0.152%

    No Known Activations