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

    Neuronpedia

    INDEX
    Explanations

    ants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     genocide
    -0.07
     Feld
    -0.07
    /session
    -0.07
     سری
    -0.06
     Thor
    -0.06
     You
    -0.06
    .You
    -0.06
     centro
    -0.06
    epend
    -0.06
     hello
    -0.06
    POSITIVE LOGITS
     inters
    0.07
    .updateDynamic
    0.06
     unnecessarily
    0.06
    олет
    0.06
    ΑΜ
    0.06
     reputable
    0.06
    况
    0.06
    enever
    0.06
     Rates
    0.06
    ัตว
    0.06
    Act Density 0.002%

    No Known Activations