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

    Neuronpedia

    INDEX
    Explanations

    following recommendations and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    0.60
    i
    0.58
    ي
    0.57
    in
    0.54
    e
    0.54
    ه
    0.53
    ה
    0.53
    Techn
    0.52
    ে
    0.52
    d
    0.52
    POSITIVE LOGITS
     Cir
    0.43
     Sincerely
    0.42
    alink
    0.42
    acas
    0.42
     CARBON
    0.41
    malı
    0.40
    bedo
    0.40
     Gum
    0.40
    gum
    0.40
     Dont
    0.39
    Act Density 0.000%

    No Known Activations