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

    Neuronpedia

    INDEX
    Explanations

    python `F` and `nn` imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻨ
    0.86
    меется
    0.85
    ッキ
    0.84
    ാ
    0.81
    cidas
    0.81
    ம்
    0.80
    ながら
    0.80
    ിൽ
    0.79
     Nakon
    0.79
    یکیشن
    0.79
    POSITIVE LOGITS
     mức
    0.79
    {{
    0.78
    }
    0.77
    }])
    0.76
     os
    0.75
    }"]
    0.73
    <
    0.73
    =
    0.71
    amount
    0.70
    lemon
    0.70
    Act Density 0.004%

    No Known Activations