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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    coding-related elements, particularly in styles and color properties.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    없이
    -0.07
     legalization
    -0.07
    uels
    -0.07
     getUser
    -0.06
    цію
    -0.06
     retention
    -0.06
     इस
    -0.06
     ilgili
    -0.06
     angle
    -0.06
    ス
    -0.06
    POSITIVE LOGITS
     Puppy
    0.07
    CFG
    0.06
    _probability
    0.06
     labs
    0.06
    Wide
    0.06
     crafts
    0.06
    لط
    0.06
     Sov
    0.06
    furt
    0.06
     Nord
    0.06
    Act Density 0.005%

    No Known Activations