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

    Neuronpedia

    INDEX
    Explanations

    constituency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     listar
    -0.08
     Liverpool
    -0.08
    _banner
    -0.07
    陸
    -0.07
     MA
    -0.07
    Thomas
    -0.07
    958
    -0.07
    locales
    -0.07
    apore
    -0.07
    _PRI
    -0.07
    POSITIVE LOGITS
     constituency
    0.07
    SWG
    0.06
    ีท
    0.06
    лении
    0.06
    i�
    0.06
    Ax
    0.06
    義
    0.06
     い
    0.06
    اهرة
    0.06
    -cond
    0.06
    Act Density 0.005%

    No Known Activations