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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     judging
    -0.06
     plan
    -0.06
     Пари
    -0.06
    nombre
    -0.06
    _Reg
    -0.06
    ilen
    -0.06
     Ubisoft
    -0.06
     youths
    -0.06
     Promotion
    -0.06
    _usb
    -0.06
    POSITIVE LOGITS
    étique
    0.07
     거야
    0.07
    ')]
    0.07
    _restrict
    0.07
    .ConnectionString
    0.06
    getPost
    0.06
    uelles
    0.06
    .INTER
    0.06
    кие
    0.06
    Decrypt
    0.06
    Act Density 0.028%

    No Known Activations