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

    Neuronpedia

    INDEX
    Explanations

    good workingenemy linesprevent too manywell-rounded personalong lineage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    éfonos
    0.80
    K
    0.80
    A
    0.76
    Pur
    0.74
    C
    0.73
    J
    0.71
    D
    0.70
    Al
    0.70
    zki
    0.70
     sklearn
    0.69
    POSITIVE LOGITS
     remedied
    0.95
    рата
    0.91
    𝒕
    0.86
    ونی
    0.82
    ет
    0.82
    ן
    0.79
     thoſe
    0.79
     whom
    0.78
    瞍
    0.78
     corrected
    0.78
    Act Density 0.001%

    No Known Activations