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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .not
    -0.07
     Areas
    -0.07
     Anaheim
    -0.07
    chest
    -0.07
    .strings
    -0.07
    ยา
    -0.07
    weekday
    -0.06
     Impossible
    -0.06
    อต
    -0.06
     آلة
    -0.06
    POSITIVE LOGITS
     иде
    0.06
    EUR
    0.06
    PG
    0.06
     bye
    0.06
    -php
    0.06
    nten
    0.06
     dětí
    0.06
     ---
    0.06
     SWAT
    0.06
    ---
    0.06
    Act Density 0.061%

    No Known Activations