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

    Neuronpedia

    INDEX
    Explanations

    Rules/Lists

    np_max-act · gemini-2.0-flash

    content related to sexual humiliation.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     詳細
    -0.06
    .md
    -0.06
     talking
    -0.06
     infographic
    -0.06
    598
    -0.06
    ania
    -0.06
    els
    -0.06
    ocracy
    -0.06
    imp
    -0.06
     Peaks
    -0.06
    POSITIVE LOGITS
     Slav
    0.07
    ='<?
    0.06
     den
    0.06
     clearfix
    0.06
     adım
    0.06
     Respect
    0.06
    /live
    0.06
     stylesheet
    0.06
    назнач
    0.06
    金
    0.06
    Act Density 0.016%

    No Known Activations