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

    Neuronpedia

    INDEX
    Explanations

    returning lost items

    np_max-act · gemini-2.0-flash

    situations involving ethical dilemmas or moral decisions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     scratched
    -0.07
    系统
    -0.07
    .sin
    -0.06
     BACKGROUND
    -0.06
    .class
    -0.06
    ，那
    -0.06
    pton
    -0.06
    thinking
    -0.06
    (tc
    -0.06
    ignum
    -0.06
    POSITIVE LOGITS
    _Group
    0.06
    _exceptions
    0.06
     upscale
    0.06
     ong
    0.06
     повітря
    0.06
    .subscription
    0.06
     guitar
    0.06
     ime
    0.06
    .module
    0.06
     spotify
    0.06
    Act Density 0.024%

    No Known Activations