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

    Neuronpedia

    INDEX
    Explanations

    time running out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    want
    -0.09
     Plano
    -0.08
    facility
    -0.08
    iversity
    -0.07
    ורת
    -0.07
    ikom
    -0.07
    virus
    -0.07
     verbal
    -0.07
     dulce
    -0.07
     Virus
    -0.07
    POSITIVE LOGITS
     खबर
    0.09
     paramount
    0.08
     خبر
    0.08
     soll's
    0.08
     արդյուն
    0.08
     أنحاء
    0.08
    երի
    0.08
     pert
    0.08
    _IRQHandler
    0.07
     permissible
    0.07
    Act Density 0.778%

    No Known Activations