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

    Neuronpedia

    INDEX
    Explanations

    any / all / any kind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    approximately
    0.45
    fourth
    0.44
    的速度
    0.44
    tournament
    0.43
    obut
    0.43
    latest
    0.43
    of
    0.43
    s
    0.42
    ness
    0.41
    ơ
    0.41
    POSITIVE LOGITS
     any
    0.60
     your
    0.53
     Any
    0.52
     all
    0.52
     любом
    0.52
     ANY
    0.51
     qualquer
    0.50
     Tabs
    0.49
    ؟
    0.48
     Batter
    0.47
    Act Density 0.000%

    No Known Activations