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

    Neuronpedia

    INDEX
    Explanations

    instances of declarative statements where a user expresses their thoughts or asks for assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    JavaScript code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CURIAM
    -0.55
    mbg
    -0.48
    󠁢
    -0.48
    Географиясе
    -0.47
     Subscribers
    -0.45
    enseits
    -0.45
     subscribers
    -0.45
    XmlAccessType
    -0.45
     IconData
    -0.44
    󠁿
    -0.44
    POSITIVE LOGITS
    Additionally
    0.43
    WebElementEntity
    0.42
    ucoup
    0.40
     supplémentaire
    0.39
    Things
    0.38
    **
    0.38
    EDIT
    0.37
     libremente
    0.37
     problemer
    0.37
    Additional
    0.37
    Act Density 0.110%

    No Known Activations