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

    Neuronpedia

    INDEX
    Explanations

    into his

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iate
    0.46
    ind
    0.46
    inned
    0.44
    inne
    0.44
    achute
    0.43
     tailles
    0.43
    るので
    0.42
    aviti
    0.42
    ernen
    0.42
     tutte
    0.42
    POSITIVE LOGITS
    0.51
     живот
    0.50
     検
    0.48
    動物
    0.47
     itth
    0.47
     Иванов
    0.47
     ကု
    0.46
    ப்பதி
    0.46
    ∗</
    0.46
     Phật
    0.45
    Act Density 0.000%

    No Known Activations