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

    Neuronpedia

    INDEX
    Explanations

    Time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _copy
    -0.06
     nob
    -0.06
     Modules
    -0.06
    unteer
    -0.06
     bird
    -0.06
    (import
    -0.06
     Nobody
    -0.06
    medicine
    -0.06
     Nets
    -0.06
    اص
    -0.05
    POSITIVE LOGITS
     mesaj
    0.07
    备注
    0.07
    .LoadScene
    0.07
     할
    0.07
    operand
    0.06
    �
    0.06
    チェ
    0.06
    pc
    0.06
    альний
    0.06
    atomic
    0.06
    Act Density 0.005%

    No Known Activations