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

    Neuronpedia

    INDEX
    Explanations

    answer

    np_max-act · gemini-2.0-flash

    explicit and harmful content involving non-consensual acts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Ross
    -0.07
     Kum
    -0.06
     خشک
    -0.06
    .setWidth
    -0.06
    .r
    -0.06
    929
    -0.06
    ());
    -0.06
    étique
    -0.06
     Ross
    -0.06
    His
    -0.06
    POSITIVE LOGITS
    lobal
    0.07
     ("-
    0.07
    émon
    0.07
     hesab
    0.07
    _candidates
    0.07
     Ди
    0.06
     Third
    0.06
    PIX
    0.06
     spouse
    0.06
    _slice
    0.06
    Act Density 0.005%

    No Known Activations