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

    Neuronpedia

    INDEX
    Explanations

    custom object properties

    np_acts-logits-general · gemini-2.5-flash-lite

    DataFrame and coding libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     is
    0.83
    _
    0.78
    ,
    0.70
    ')
    0.68
     =
    0.62
     बॉलीवुड
    0.61
    }=\
    0.59
     médicos
    0.59
     svenska
    0.59
    )
    0.58
    POSITIVE LOGITS
    ב
    1.13
    (
    1.04
    ه
    1.01
    and
    0.93
    it
    0.86
    न
    0.86
    د
    0.84
    ন
    0.84
    ال
    0.83
    at
    0.82
    Act Density 0.004%

    No Known Activations