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

    Neuronpedia

    INDEX
    Explanations

    Sampling Frame, perilous mission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EXISTS
    0.45
    ället
    0.42
    ંક
    0.41
     Gene
    0.39
    ->$
    0.39
    وجود
    0.38
     esiste
    0.38
    飏
    0.38
     vů
    0.38
     noun
    0.37
    POSITIVE LOGITS
     Hab
    0.47
     hab
    0.43
    hab
    0.42
    gaz
    0.40
    স্তাফ
    0.40
    Hab
    0.40
    rzeć
    0.39
    Gaz
    0.39
    рте
    0.39
    hairs
    0.38
    Act Density 0.000%

    No Known Activations