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

    Neuronpedia

    INDEX
    Explanations

    start of model output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     présente
    0.75
    Date
    0.73
    Location
    0.72
    are
    0.68
    “
    0.68
    غ
    0.65
    ْ
    0.65
    }
    0.65
     apparaît
    0.64
    on
    0.64
    POSITIVE LOGITS
    ת
    0.77
    드의
    0.75
    но
    0.74
    ى
    0.73
    O
    0.69
    어
    0.67
    ﺘ
    0.65
    스를
    0.64
    ன்
    0.64
    ש
    0.63
    Act Density 0.410%

    No Known Activations