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

    Neuronpedia

    INDEX
    Explanations

    ultimately proven / unforeseen events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    гідно
    0.50
    льном
    0.46
    ви
    0.46
    ău
    0.45
     Републи
    0.42
    डू
    0.42
    жник
    0.42
    ق
    0.42
    selfobj
    0.42
    рко
    0.41
    POSITIVE LOGITS
    0
    0.53
    ctions
    0.52
    ifat
    0.47
    ’
    0.46
    omics
    0.45
    :
    0.43
    hood
    0.43
     dakkh
    0.42
     知
    0.41
     uitgen
    0.41
    Act Density 0.001%

    No Known Activations