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

    Neuronpedia

    INDEX
    Explanations

    Google Search

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Smith
    0.62
    Combine
    0.59
    Elli
    0.59
     ตุ
    0.58
    Aus
    0.58
    Bis
    0.57
    डू
    0.56
    uettes
    0.56
    faux
    0.55
    DP
    0.54
    POSITIVE LOGITS
     setor
    0.64
     ASPECT
    0.63
     DIST
    0.63
    ۇر
    0.62
     சோதனை
    0.62
     condição
    0.59
     mlflow
    0.59
     Anbieter
    0.59
     вечером
    0.59
     церков
    0.59
    Act Density 0.000%

    No Known Activations