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

    Neuronpedia

    INDEX
    Explanations

    already whenever precise Attention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     redact
    0.38
     Pla
    0.37
    ብሰ
    0.37
     podendo
    0.37
     gốc
    0.36
     πως
    0.36
     sams
    0.36
     Sams
    0.36
     Rimini
    0.36
     ছিলনা
    0.35
    POSITIVE LOGITS
    lcl
    0.46
    aktor
    0.41
    pte
    0.41
    ah
    0.40
    low
    0.39
    ectors
    0.39
    rta
    0.38
    usine
    0.37
    地区
    0.37
    nard
    0.37
    Act Density 0.002%

    No Known Activations