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

    Neuronpedia

    INDEX
    Explanations

    once time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fractional
    -0.07
     Кост
    -0.06
     �
    -0.06
    昭和
    -0.06
     cyc
    -0.06
     aden
    -0.06
    scenario
    -0.06
    áce
    -0.06
     pnl
    -0.06
    číta
    -0.06
    POSITIVE LOGITS
     birisi
    0.07
     Supern
    0.07
    dle
    0.06
    Guest
    0.06
    maybe
    0.06
    amat
    0.06
    abra
    0.06
     silently
    0.06
     इनक
    0.06
    wait
    0.06
    Act Density 0.014%

    No Known Activations