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

    Neuronpedia

    INDEX
    Explanations

    Python inspect module

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jalis
    0.51
     emitter
    0.50
     выво
    0.50
     অতিক্রম
    0.50
     insignia
    0.48
     exprim
    0.48
     skladu
    0.48
    findBy
    0.47
     reunir
    0.46
     иллюстрация
    0.46
    POSITIVE LOGITS
    ก
    0.57
    ด
    0.55
    тів
    0.54
    sion
    0.53
    sel
    0.52
    erede
    0.52
    thia
    0.52
    week
    0.51
    जार
    0.51
    тата
    0.50
    Act Density 0.000%

    No Known Activations