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

    Neuronpedia

    INDEX
    Explanations

    punctuation and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.76
     caused
    0.75
     that
    0.74
    :
    0.71
     ؛
    0.70
     the
    0.70
     Unterschied
    0.65
     unaffected
    0.65
    :",
    0.64
    ;
    0.64
    POSITIVE LOGITS
     மற்றும்
    0.68
    ↵↵
    0.66
    ahiya
    0.66
     protagonisti
    0.66
    ovati
    0.64
     ecco
    0.63
    をご紹介
    0.62
     గారి
    0.61
     kurulum
    0.58
     prvo
    0.58
    Act Density 0.044%

    No Known Activations