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

    Neuronpedia

    INDEX
    Explanations

    dream song and classics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scratched
    0.47
     ଭ
    0.40
     रमा
    0.39
     obliterated
    0.39
     possessed
    0.39
     forgot
    0.38
    SXml
    0.38
     newToken
    0.37
     discarded
    0.37
    esting
    0.37
    POSITIVE LOGITS
    wide
    0.58
     širo
    0.56
     wide
    0.55
    Apart
    0.55
     Wide
    0.52
    WIDE
    0.52
     apart
    0.50
     широ
    0.50
    Wide
    0.50
     Apart
    0.49
    Act Density 0.000%

    No Known Activations