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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     advises
    -0.07
    ']")↵
    -0.07
    ')])↵
    -0.07
     rarity
    -0.06
    nam
    -0.06
    .il
    -0.06
    ╩
    -0.06
    >xpath
    -0.06
    というもの
    -0.06
    (Debug
    -0.06
    POSITIVE LOGITS
    usted
    0.07
    ти
    0.07
     Fibonacci
    0.07
     парти
    0.07
     Fucking
    0.07
    жу
    0.07
    clipboard
    0.06
     Decay
    0.06
    serial
    0.06
     четы
    0.06
    Act Density 0.045%

    No Known Activations