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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    628
    -0.07
     insulated
    -0.07
    悟
    -0.06
    >R
    -0.06
    ｣
    -0.06
    Radio
    -0.06
    .commands
    -0.06
     dünyanın
    -0.06
     mathematics
    -0.06
    birthdate
    -0.06
    POSITIVE LOGITS
    _Tag
    0.07
     文
    0.06
    Virgin
    0.06
    /name
    0.06
     Virgin
    0.06
    ابی
    0.06
     Você
    0.06
    angen
    0.06
     απ
    0.06
     bookmarks
    0.06
    Act Density 0.163%

    No Known Activations