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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zen
    -0.06
    _latitude
    -0.06
     Pe
    -0.06
     ordinary
    -0.06
     debilitating
    -0.06
    Pe
    -0.06
    汽车
    -0.06
     legendary
    -0.06
    Г
    -0.06
    库
    -0.06
    POSITIVE LOGITS
     Buccane
    0.07
    christ
    0.07
     Zot
    0.07
    maktan
    0.07
     anyhow
    0.07
     saddened
    0.07
     Morav
    0.07
    -ф
    0.07
    ласти
    0.06
     serait
    0.06
    Act Density 0.385%

    No Known Activations