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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     лише
    -0.07
    because
    -0.07
     Utilities
    -0.06
    .segment
    -0.06
    		↵
    -0.06
    _stdout
    -0.06
    拳
    -0.06
     because
    -0.06
    ↵	↵
    -0.06
    (...)↵
    -0.06
    POSITIVE LOGITS
    ouis
    0.06
     bf
    0.06
     szy
    0.06
    وروب
    0.06
    _SYSTEM
    0.06
    SY
    0.06
     спів
    0.06
     út
    0.06
     влас
    0.06
    etype
    0.05
    Act Density 0.028%

    No Known Activations