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

    Neuronpedia

    INDEX
    Explanations

    Code/numerical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dragons
    -0.07
    insic
    -0.06
    /editor
    -0.06
     electr
    -0.06
     долж
    -0.06
     editor
    -0.06
     بسیاری
    -0.06
     дуже
    -0.06
     ฟร
    -0.06
    Junior
    -0.06
    POSITIVE LOGITS
     ==(
    0.07
     stringValue
    0.07
    :model
    0.07
    (pol
    0.07
    (Model
    0.07
     discourage
    0.07
     Alias
    0.07
    =[]
    0.06
     reused
    0.06
    pak
    0.06
    Act Density 0.019%

    No Known Activations