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

    Neuronpedia

    INDEX
    Explanations

    understanding youtube

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nike
    0.45
    ultz
    0.45
     Kaiser
    0.44
    KE
    0.44
    有点
    0.44
    Nike
    0.43
     Arbitration
    0.43
     Surplus
    0.43
    ష
    0.43
     Wilson
    0.42
    POSITIVE LOGITS
     cryptography
    0.52
    ﺔ
    0.48
    ।
    0.48
     aluno
    0.47
     consciously
    0.46
     trimestre
    0.46
     crescimento
    0.45
     departures
    0.45
    ។
    0.45
     développement
    0.45
    Act Density 0.004%

    No Known Activations