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

    Neuronpedia

    INDEX
    Explanations

    self in python code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    1.27
    ↵
    1.16
    .
    1.06
    ת
    0.91
    _
    0.90
    ী
    0.89
    ak
    0.83
    x
    0.82
    3
    0.81
    )
    0.80
    POSITIVE LOGITS
     was
    0.88
    to
    0.88
     तरह
    0.79
    ുമോ
    0.76
    inama
    0.75
     리그
    0.75
     were
    0.73
    سون
    0.73
    ᅨ
    0.73
    histo
    0.72
    Act Density 0.021%

    No Known Activations