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

    Neuronpedia

    INDEX
    Explanations

    diverse text fragments

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ...,
    0.84
    squares
    0.77
    ₂,
    0.74
     INTEGER
    0.74
    xmin
    0.72
    themes
    0.71
    tempo
    0.68
    pools
    0.68
     квадра
    0.68
    ...",
    0.67
    POSITIVE LOGITS
    .
    0.71
    ↵
    0.68
    ור
    0.66
    ב
    0.65
     オレンジ
    0.65
     adlı
    0.63
    חס
    0.62
    ักษ
    0.60
     från
    0.60
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.60
    Act Density 0.000%

    No Known Activations