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

    Neuronpedia

    INDEX
    Explanations

    frame tool management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     российский
    1.00
     экспер
    0.95
    тных
    0.93
     немец
    0.91
     frizz
    0.90
    INE
    0.90
    тным
    0.89
    แบ่ง
    0.87
     российских
    0.86
    торое
    0.86
    POSITIVE LOGITS
     riguard
    1.03
    Kalau
    0.98
     riguarda
    0.96
    ’’
    0.95
    ğini
    0.92
    ningen
    0.91
     quelcon
    0.91
    Selain
    0.89
    ’
    0.88
    ؛
    0.88
    Act Density 0.001%

    No Known Activations