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

    Neuronpedia

    INDEX
    Explanations

    Specific names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    villa
    -0.07
    深い
    -0.07
    ク
    -0.07
     ling
    -0.07
    Whenever
    -0.06
     Best
    -0.06
     않는다
    -0.06
    IÓN
    -0.06
     לימודי
    -0.06
     pierced
    -0.06
    POSITIVE LOGITS
     nod
    0.08
     NR
    0.07
     cfg
    0.07
    مستثمر
    0.07
    .environment
    0.07
    سرائيل
    0.07
     currentState
    0.06
    退还
    0.06
    notif
    0.06
    Period
    0.06
    Act Density 0.000%

    No Known Activations