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

    Neuronpedia

    INDEX
    Explanations

    code and technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     senses
    -0.08
    Retail
    -0.07
    rones
    -0.07
     openness
    -0.07
    blink
    -0.06
     words
    -0.06
    Chinese
    -0.06
    avg
    -0.06
     authorization
    -0.06
     museums
    -0.06
    POSITIVE LOGITS
    (",",
    0.07
    sortBy
    0.07
    ічної
    0.07
     careless
    0.07
    览
    0.06
     ="
    0.06
    "strings
    0.06
    (expr
    0.06
    触
    0.06
     مشاهده
    0.06
    Act Density 0.000%

    No Known Activations