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

    Neuronpedia

    INDEX
    Explanations

    multilingual texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .writeln
    -0.08
    ＿
    -0.07
    aversable
    -0.07
    FullName
    -0.06
    _coverage
    -0.06
     racial
    -0.06
    thumbnails
    -0.06
    ByteArray
    -0.06
    _PROCESS
    -0.06
     Child
    -0.06
    POSITIVE LOGITS
     debacle
    0.07
    reed
    0.07
     defenders
    0.07
     indign
    0.06
     دوست
    0.06
    充
    0.06
     reife
    0.06
     fds
    0.06
    essen
    0.06
     продукты
    0.06
    Act Density 0.022%

    No Known Activations