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

    Neuronpedia

    INDEX
    Explanations

    Natural Language Processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    效应
    1.09
     TECHNICAL
    0.95
    age
    0.94
    penet
    0.93
    技術
    0.92
    Technical
    0.91
    然後
    0.90
    岖
    0.90
     redeemed
    0.89
    technical
    0.88
    POSITIVE LOGITS
    те
    0.78
    l
    0.77
    다고
    0.76
     occurring
    0.73
    lijke
    0.72
    __':
    0.71
    dür
    0.70
    lijk
    0.70
    lk
    0.69
    dol
    0.68
    Act Density 0.084%

    No Known Activations