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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     незавершена
    -0.82
    estacks
    -0.71
     فريبيس
    -0.69
     utafitiHapana
    -0.67
    LookAnd
    -0.64
    хьтан
    -0.64
     @"/
    -0.63
    Autoritní
    -0.60
    下载附件
    -0.59
     مرئيه
    -0.59
    POSITIVE LOGITS
     Perfection
    0.58
     multiplicative
    0.54
     Relax
    0.52
     Bueno
    0.50
     Standards
    0.47
     MediaType
    0.47
     Missions
    0.46
     Diversity
    0.46
    ペース
    0.46
     e
    0.45
    Act Density 0.003%

    No Known Activations