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

    Neuronpedia

    INDEX
    Explanations

    parenthetical words and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     evitare
    0.56
     éviter
    0.55
     possono
    0.54
     vermeiden
    0.52
    графія
    0.52
     assertEquals
    0.51
    避け
    0.51
     avoiding
    0.49
    asciiPanel
    0.49
     avoids
    0.48
    POSITIVE LOGITS
    Id
    0.57
    ,
    0.49
    /
    0.46
    Daily
    0.46
    aka
    0.46
     brutal
    0.45
    Email
    0.45
    Color
    0.44
    ild
    0.43
    ves
    0.43
    Act Density 0.000%

    No Known Activations