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

    Neuronpedia

    INDEX
    Explanations

    perpetuate stereotypes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    কর্ম
    0.52
    prim
    0.48
    ви
    0.47
    вини
    0.46
     لوبوي
    0.44
    MODEL
    0.44
    俚
    0.43
    plug
    0.42
     panor
    0.42
    कर्म
    0.42
    POSITIVE LOGITS
    ED
    0.48
     प्रमाणात
    0.47
    .*/
    0.45
     breasts
    0.44
     countries
    0.43
     ##
    0.43
     //.
    0.42
     */
    0.42
     Destroy
    0.42
     the
    0.41
    Act Density 0.002%

    No Known Activations