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
     (),↵
    -0.07
    лев
    -0.07
     MEN
    -0.07
    388
    -0.07
     Araştır
    -0.06
    debug
    -0.06
     рождения
    -0.06
     Allies
    -0.06
    ريق
    -0.06
    cod
    -0.06
    POSITIVE LOGITS
    .setTag
    0.07
    ervatives
    0.07
    localctx
    0.06
    .vue
    0.06
    ','"+
    0.06
    .toUpperCase
    0.06
     Hond
    0.06
    Increment
    0.06
    marginTop
    0.06
    _guess
    0.06
    Act Density 0.014%

    No Known Activations