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

    Neuronpedia

    INDEX
    Explanations

    pretty sure my

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dissu
    0.50
    ER
    0.47
     nonzero
    0.44
    KE
    0.44
    CCOCC
    0.41
     multiply
    0.41
     griev
    0.40
    öny
    0.40
    JE
    0.40
     CRIMINAL
    0.40
    POSITIVE LOGITS
    ڑی
    0.45
     specification
    0.44
    itatud
    0.44
    actéristiques
    0.44
    specification
    0.44
     périphérique
    0.44
     Specification
    0.43
    اویز
    0.42
    Specification
    0.41
    Widget
    0.41
    Act Density 0.002%

    No Known Activations