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

    Neuronpedia

    INDEX
    Explanations

    their

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Let
    -0.07
    .fixed
    -0.06
    udoku
    -0.06
     Impact
    -0.06
     Grat
    -0.06
    scanner
    -0.06
     Efficient
    -0.06
     lotion
    -0.06
    FAQ
    -0.06
     Chains
    -0.06
    POSITIVE LOGITS
     ※
    0.07
     persona
    0.06
    .constant
    0.06
     Korean
    0.06
    กร
    0.06
     acı
    0.06
    报
    0.06
     extrem
    0.06
     😉
    0.06
    抵
    0.06
    Act Density 0.006%

    No Known Activations