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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mongolia
    -0.08
     correspondent
    -0.07
     Benton
    -0.07
    osemite
    -0.06
     XT
    -0.06
     infringement
    -0.06
     apologized
    -0.06
     LONG
    -0.06
     aggression
    -0.06
     concentrate
    -0.06
    POSITIVE LOGITS
    .sim
    0.08
    @qq
    0.08
    \Api
    0.07
    /dr
    0.07
    溺
    0.07
    阿拉
    0.07
     Static
    0.07
    ולם
    0.07
    .junit
    0.07
    天涯
    0.06
    Act Density 0.002%

    No Known Activations