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

    Neuronpedia

    INDEX
    Explanations

    defining code environments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    H
    0.46
    Greg
    0.46
    G
    0.45
    via
    0.44
    HS
    0.43
    e
    0.42
    Design
    0.42
    0.41
    OR
    0.41
    r
    0.41
    POSITIVE LOGITS
     गलत
    0.48
     vasculaire
    0.47
    ᖕ
    0.47
     chiamato
    0.47
    imcoords
    0.46
     veramente
    0.46
     excepciones
    0.46
     〢
    0.45
     耐
    0.45
     kut
    0.44
    Act Density 0.000%

    No Known Activations