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

    Neuronpedia

    INDEX
    Explanations

    form or forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Př
    1.74
     وعلى
    1.64
    ф
    1.55
     berbentuk
    1.48
     Př
    1.48
     Ч
    1.47
    Π
    1.47
    ін
    1.41
    री
    1.41
    ž
    1.40
    POSITIVE LOGITS
    으로써
    2.36
    م
    2.03
    gebung
    1.99
    dated
    1.66
     станов
    1.63
    t
    1.63
    RENCE
    1.63
    噌
    1.61
     geométricas
    1.60
    nance
    1.59
    Act Density 0.206%

    No Known Activations