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

    Neuronpedia

    INDEX
    Explanations

    specific nouns followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     without
    0.59
     belirli
    0.53
     без
    0.52
     granular
    0.51
     dengan
    0.49
     specific
    0.47
     Без
    0.46
     WITH
    0.45
     WITHOUT
    0.45
     bestimmten
    0.45
    POSITIVE LOGITS
     والذي
    0.77
     famed
    0.75
     nonché
    0.72
     والتي
    0.71
     nicknamed
    0.70
    ,—
    0.66
     commemorated
    0.65
     convened
    0.65
     occasioned
    0.64
    (!
    0.64
    Act Density 0.715%

    No Known Activations