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

    Neuronpedia

    INDEX
    Explanations

    computer software

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    m
    0.83
    }}(\
    0.77
    }}_{\
    0.75
     १५
    0.75
     sidelined
    0.75
     मोट
    0.74
     बह
    0.74
     इतर
    0.74
     отдельно
    0.74
     заболеваний
    0.73
    POSITIVE LOGITS
    تان
    1.00
    телно
    0.94
    لا
    0.92
    ました
    0.92
    요
    0.92
    ுடன்
    0.91
    تش
    0.89
    sortie
    0.81
    विषयी
    0.79
    していて
    0.79
    Act Density 0.000%

    No Known Activations