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

    Neuronpedia

    INDEX
    Explanations

    parentheses/em-dashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ariat
    -0.07
    ンディ
    -0.07
    oug
    -0.06
    ereg
    -0.06
    etim
    -0.06
    esin
    -0.06
    rlen
    -0.06
     rivalry
    -0.06
    validation
    -0.06
    inç
    -0.06
    POSITIVE LOGITS
    .Bad
    0.07
     अव
    0.06
    .Vert
    0.06
    Hmm
    0.06
     чемпион
    0.06
     Đà
    0.06
    -Assad
    0.06
    .SelectSingleNode
    0.06
    豪
    0.06
     GAL
    0.06
    Act Density 0.271%

    No Known Activations