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

    Neuronpedia

    INDEX
    Explanations

    Seneca, Sisyphus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     migli
    0.61
     reduce
    0.59
     semplicemente
    0.59
     просто
    0.58
     seguenti
    0.58
     inguinal
    0.58
     rimane
    0.57
     shale
    0.57
     segera
    0.56
     fielding
    0.56
    POSITIVE LOGITS
    v
    0.67
    f
    0.64
    s
    0.64
    d
    0.62
    p
    0.62
    x
    0.59
    t
    0.57
    l
    0.57
    y
    0.54
    F
    0.54
    Act Density 0.000%

    No Known Activations