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

    Neuronpedia

    INDEX
    Explanations

    Wall

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fce
    -0.07
    boro
    -0.07
     ry
    -0.07
    322
    -0.06
    ller
    -0.06
    _PO
    -0.06
     endeavor
    -0.06
     Autos
    -0.06
    Emily
    -0.06
     murder
    -0.06
    POSITIVE LOGITS
    论文
    0.07
    .assertIsNot
    0.06
    .OnClickListener
    0.06
     IsPlainOldData
    0.06
     Mazda
    0.06
    (Token
    0.06
     tuyên
    0.06
     کتاب
    0.06
     Musik
    0.06
    !.↵↵
    0.06
    Act Density 0.002%

    No Known Activations