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

    Neuronpedia

    INDEX
    Explanations

    community

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ideal
    -0.07
     Room
    -0.07
    vice
    -0.07
     tôn
    -0.06
    dice
    -0.06
    _Parameter
    -0.06
    tics
    -0.06
     Superman
    -0.06
     prevail
    -0.06
    infinity
    -0.06
    POSITIVE LOGITS
     захворювання
    0.07
     cough
    0.07
     каче
    0.06
    \"\
    0.06
    екотор
    0.06
    -original
    0.06
    esseract
    0.06
     regeneration
    0.06
    อกาส
    0.06
    .getOutputStream
    0.06
    Act Density 0.099%

    No Known Activations