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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ups
    -0.07
    Vý
    -0.07
    Mor
    -0.07
    -colored
    -0.06
    .setStatus
    -0.06
    ków
    -0.06
    _execute
    -0.06
     concat
    -0.06
    Ser
    -0.06
    _known
    -0.06
    POSITIVE LOGITS
    ):(
    0.07
     apocalypse
    0.06
    934
    0.06
    (signal
    0.06
     susceptible
    0.06
    3
    0.06
     seh
    0.06
    oomla
    0.06
     appart
    0.06
     numeral
    0.06
    Act Density 0.063%

    No Known Activations