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

    Neuronpedia

    INDEX
    Explanations

    language structures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dej
    -0.06
    π
    -0.06
     Θε
    -0.06
    �
    -0.06
    punk
    -0.06
    zm
    -0.06
     анализ
    -0.06
    phylum
    -0.06
     esk
    -0.06
     ポ
    -0.06
    POSITIVE LOGITS
     konkrét
    0.07
     JsonResult
    0.07
    .invoke
    0.06
     Sentinel
    0.06
     funciona
    0.06
     continue
    0.06
    (Canvas
    0.06
    .method
    0.06
     oversee
    0.06
     discontinued
    0.06
    Act Density 0.005%

    No Known Activations