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

    Neuronpedia

    INDEX
    Explanations

    Core Definition, Key Features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    1.13
    ：
    0.97
    ):
    0.91
    /
    0.89
    }:
    0.88
    ]:
    0.88
    ’:
    0.81
    ],
    0.80
    ,
    0.79
    ”:
    0.78
    POSITIVE LOGITS
     sağlıklı
    0.66
     neler
    0.62
     ১১
    0.61
     seguimos
    0.61
     tři
    0.61
    ataya
    0.60
     čty
    0.60
     hechos
    0.59
    ividades
    0.59
     centímetros
    0.59
    Act Density 0.755%

    No Known Activations