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

    Neuronpedia

    INDEX
    Explanations

    code and programming concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     s
    0.71
    정에
    0.68
     constellation
    0.64
    정이
    0.62
    azines
    0.61
    ird
    0.60
    }\,\
    0.58
    ])):
    0.58
    est
    0.57
    ]).
    0.57
    POSITIVE LOGITS
     comentários
    0.89
     execução
    0.88
     söz
    0.83
     především
    0.81
     carrinho
    0.81
    icción
    0.80
     চোখের
    0.79
    đenja
    0.78
     Осо
    0.78
     ות
    0.78
    Act Density 0.038%

    No Known Activations