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

    Neuronpedia

    INDEX
    Explanations

    constantly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Only
    -0.07
    ữ
    -0.07
     Việt
    -0.06
    ﺈ
    -0.06
    ©
    -0.06
     Tes
    -0.06
     Following
    -0.06
    yne
    -0.06
    _piece
    -0.06
    漫画
    -0.06
    POSITIVE LOGITS
     курс
    0.07
    /car
    0.07
    /{}/
    0.07
    Firstname
    0.07
    进门
    0.06
     thuisontvangst
    0.06
    脑子
    0.06
    ophil
    0.06
     crusher
    0.06
    ')}
    0.06
    Act Density 0.012%

    No Known Activations