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

    Neuronpedia

    INDEX
    Explanations

    therapy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    channel
    -0.07
    má
    -0.07
     domest
    -0.06
    nila
    -0.06
    .extension
    -0.06
    ьи
    -0.06
    Translations
    -0.06
    amacare
    -0.06
     liaison
    -0.06
    .pin
    -0.06
    POSITIVE LOGITS
     abbreviated
    0.07
    desired
    0.06
     skoro
    0.06
     YORK
    0.06
    ISE
    0.06
    _FILENAME
    0.06
    ”).
    0.06
     تلف
    0.06
     Ginger
    0.06
    Gravity
    0.06
    Act Density 0.000%

    No Known Activations