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

    Neuronpedia

    INDEX
    Explanations

    https:// links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    -2.48
    }(\
    -1.77
     wohin
    -1.67
    🪐
    -1.49
     or
    -1.41
     lhe
    -1.36
     тип
    -1.36
     penyakit
    -1.35
     distru
    -1.35
    หรือ
    -1.34
    POSITIVE LOGITS
    </i>
    2.64
    .
    1.98
    like
    1.95
    according
    1.93
    Approximately
    1.84
    峮
    1.83
    _
    1.80
    following
    1.79
    actually
    1.78
    Additionally
    1.77
    Act Density 0.003%

    No Known Activations