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

    Neuronpedia

    INDEX
    Explanations

    loop termination `i`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ruktur
    1.38
     faptul
    1.34
    _
    1.33
    s
    1.20
    eta
    1.16
    eted
    1.14
    el
    1.13
     K
    1.12
    ato
    1.11
    ul
    1.09
    POSITIVE LOGITS
     σύμφωνα
    1.27
    ит
    1.27
    ли
    1.13
    ад
    1.13
     financeira
    1.13
    цы
    1.12
    лиги
    1.11
     gráfica
    1.11
     podamos
    1.11
    и
    1.11
    Act Density 0.003%

    No Known Activations