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

    Neuronpedia

    INDEX
    Explanations

    fits into understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     هنت
    0.61
     chom
    0.48
     Columb
    0.48
    enek
    0.47
     Domen
    0.46
    organic
    0.46
     Marquis
    0.46
     Vene
    0.45
    亨
    0.45
     Reinh
    0.45
    POSITIVE LOGITS
     strlen
    0.59
    ლ
    0.46
    US
    0.45
     widths
    0.45
     angepasst
    0.42
    }});
    0.41
    OCKET
    0.40
    LE
    0.40
    {$
    0.40
    िश्वत
    0.39
    Act Density 0.001%

    No Known Activations