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

    Neuronpedia

    INDEX
    Explanations

    you have or want

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wości
    0.70
     conscience
    0.66
    ਵੀ
    0.66
     decomposition
    0.65
    요
    0.64
     altın
    0.63
    ώς
    0.63
    øre
    0.61
     प्रतिमा
    0.61
    ితో
    0.60
    POSITIVE LOGITS
     Peel
    0.78
    )}
    0.71
     ದು
    0.69
    )}$
    0.67
     Peck
    0.67
    Scient
    0.66
     Transcript
    0.66
     பத்திர
    0.66
    Transcript
    0.66
     tràn
    0.65
    Act Density 0.026%

    No Known Activations