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

    Neuronpedia

    INDEX
    Explanations

    questions starting with what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ა
    0.74
    ir
    0.73
    ر
    0.70
     одна
    0.70
     формы
    0.70
     όλα
    0.69
    การ
    0.68
     لمبے
    0.67
    િસ
    0.66
    カイブ
    0.66
    POSITIVE LOGITS
    কে
    0.92
    }
    0.82
    q
    0.81
    },
    0.79
    ﺭ
    0.79
    help
    0.77
     are
    0.75
    _
    0.74
    }$.
    0.72
    ()
    0.70
    Act Density 0.760%

    No Known Activations