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

    Neuronpedia

    INDEX
    Explanations

    Gotham Comedy, Pali Coast, Alpaca

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    al
    0.57
    os
    0.57
    ong
    0.52
    ori
    0.52
    从而
    0.51
    trab
    0.50
    và
    0.50
    θα
    0.50
    ತೆ
    0.50
    berg
    0.49
    POSITIVE LOGITS
     be
    0.66
     piccoli
    0.57
    ן
    0.57
     ameryka
    0.56
     acht
    0.55
    ैन
    0.55
     trialComponents
    0.55
    ₺
    0.54
     subpoena
    0.54
     immunoprec
    0.54
    Act Density 0.041%

    No Known Activations