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

    Neuronpedia

    INDEX
    Explanations

    but it, God communicated, cautious policy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     domést
    0.52
     próxima
    0.50
    খান
    0.49
     thả
    0.46
    ísima
    0.46
    lastCursor
    0.45
     Sparse
    0.45
    inati
    0.44
    ọng
    0.43
     Synthesis
    0.42
    POSITIVE LOGITS
    since
    0.50
     ಏಕೆಂದರೆ
    0.49
    Worked
    0.49
    Drink
    0.48
    OMET
    0.48
    TERS
    0.48
    supp
    0.47
    Membership
    0.47
    Addo
    0.47
     Поскольку
    0.47
    Act Density 0.005%

    No Known Activations