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

    Neuronpedia

    INDEX
    Explanations

    branch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oklyn
    -0.07
    Deserializer
    -0.07
    -solving
    -0.07
    223
    -0.07
    _FACT
    -0.07
     Đông
    -0.06
     phẩm
    -0.06
     Razor
    -0.06
     Forge
    -0.06
     پرداخت
    -0.06
    POSITIVE LOGITS
    urahan
    0.06
     babe
    0.06
     suf
    0.06
     cheapest
    0.06
     unavoid
    0.06
    %',
    0.06
     kara
    0.05
     epis
    0.05
     tempting
    0.05
    .fail
    0.05
    Act Density 0.008%

    No Known Activations