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

    Neuronpedia

    INDEX
    Explanations

    conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    漫画
    -0.06
    ока
    -0.06
    ジュ
    -0.06
    �
    -0.06
     있어
    -0.06
     слив
    -0.06
    'est
    -0.06
    .getX
    -0.06
    ⠀⠀
    -0.06
    上が
    -0.06
    POSITIVE LOGITS
    rub
    0.07
     annually
    0.07
    .height
    0.07
     segreg
    0.06
     winters
    0.06
     SMS
    0.06
    ,ll
    0.06
    [field
    0.06
     oblig
    0.06
    gzip
    0.06
    Act Density 0.052%

    No Known Activations