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

    Neuronpedia

    INDEX
    Explanations

    League

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.06
    i
    1.01
    ka
    0.95
    m
    0.94
    y
    0.89
    ur
    0.86
    ar
    0.85
    g
    0.84
    l
    0.84
    n
    0.82
    POSITIVE LOGITS
     μαγγ
    0.85
    屋内
    0.82
     renderEncoder
    0.81
    淳
    0.80
     Progress
    0.80
    ల
    0.80
     Champ
    0.80
     festivities
    0.78
     Progressives
    0.77
     COMPO
    0.76
    Act Density 0.000%

    No Known Activations