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

    Neuronpedia

    INDEX
    Explanations

    Caesar

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     toda
    -0.08
    lediği
    -0.07
     ine
    -0.07
    <HTMLInputElement
    -0.07
    -inspired
    -0.06
    نین
    -0.06
     Рас
    -0.06
     přibliž
    -0.06
    ently
    -0.06
     evoke
    -0.06
    POSITIVE LOGITS
     Caesar
    0.08
    acr
    0.08
    akk
    0.07
    أس
    0.07
    arr
    0.07
     AK
    0.07
    aland
    0.07
     ARISING
    0.07
    _Insert
    0.07
    esar
    0.07
    Act Density 0.002%

    No Known Activations