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

    Neuronpedia

    INDEX
    Explanations

    sexual and violent content

    np_max-act · gemini-2.0-flash

    explicit and sexual scenarios involving power dynamics.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Doing
    -0.06
     電
    -0.06
    credit
    -0.06
    lsa
    -0.06
     insights
    -0.06
    Div
    -0.06
     ступ
    -0.06
    Application
    -0.06
    iect
    -0.06
     triples
    -0.06
    POSITIVE LOGITS
    _PRESENT
    0.07
    :\\
    0.06
     Inherits
    0.06
    /photos
    0.06
    <_
    0.06
     ammunition
    0.06
     اتفاق
    0.06
     infographic
    0.06
     外
    0.06
    анием
    0.06
    Act Density 0.100%

    No Known Activations