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

    Neuronpedia

    INDEX
    Explanations

    tokens context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     factories
    0.28
     peeling
    0.26
     Botox
    0.26
     pedicure
    0.26
     prostitution
    0.26
     Schengen
    0.25
    ષ્ટ
    0.25
     unfilled
    0.25
     sbParams
    0.25
     HeLa
    0.25
    POSITIVE LOGITS
    а
    0.30
    Ian
    0.29
    ör
    0.28
    ota
    0.27
    user
    0.27
    islav
    0.27
    ør
    0.27
    astien
    0.27
    Liam
    0.27
    son
    0.27
    Act Density 0.001%

    No Known Activations