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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash

    technical discussions related to programming and code issues.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ILING
    -0.07
    iling
    -0.07
     diminishing
    -0.06
    -0.06
     lost
    -0.06
    bred
    -0.06
     Defines
    -0.06
    istics
    -0.06
     SOP
    -0.06
     trickle
    -0.06
    POSITIVE LOGITS
     cé
    0.07
    委员
    0.07
     bon
    0.06
     澳
    0.06
     journal
    0.06
     filthy
    0.06
     помощ
    0.06
     кіль
    0.06
     strate
    0.06
     jogo
    0.06
    Act Density 0.061%

    No Known Activations