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

    Neuronpedia

    INDEX
    Explanations

    | CPC"}, "Makeup|", "column names"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ם
    2.23
    ים
    2.14
     minorities
    2.08
    lings
    1.95
     patrons
    1.95
     realities
    1.94
    s
    1.92
    すすめ
    1.89
     chinos
    1.87
     carriages
    1.84
    POSITIVE LOGITS
     suatu
    1.92
    urilor
    1.92
    ​]]
    1.89
    urile
    1.82
     peau
    1.80
    botao
    1.79
     तरह
    1.78
    nên
    1.78
    мень
    1.77
    Bước
    1.77
    Act Density 0.191%

    No Known Activations