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

    Neuronpedia

    INDEX
    Explanations

    placeholder comments like TODO or FIXME

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᖇ
    0.38
     ję
    0.38
    ₂,
    0.36
    वते
    0.36
    ккей
    0.35
    вец
    0.35
    شده
    0.35
    𒉺
    0.35
     wiederum
    0.35
    ғ
    0.35
    POSITIVE LOGITS
     TODO
    1.32
    TODO
    1.31
     FIXME
    1.03
     simplistic
    0.88
     Assuming
    0.83
    这里
    0.80
    todo
    0.80
    假設
    0.79
    假设
    0.78
     placeholder
    0.77
    Act Density 0.048%

    No Known Activations