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

    Neuronpedia

    INDEX
    Explanations

    isolated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lotion
    -0.08
     souligne
    -0.08
     Lager
    -0.08
     kai
    -0.08
     auprès
    -0.08
    shipping
    -0.08
    归
    -0.07
     kan
    -0.07
     futuro
    -0.07
    sku
    -0.07
    POSITIVE LOGITS
    _interrupt
    0.09
    aneous
    0.09
     Interrupt
    0.09
     interruptions
    0.09
     الكس
    0.08
     нарушения
    0.08
     imperfections
    0.08
     interruption
    0.08
     interrup
    0.08
    itu
    0.08
    Act Density 0.002%

    No Known Activations