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

    Neuronpedia

    INDEX
    Explanations

    phrases related to intent and meaning in conversations

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

    not know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.53
    principalColumn
    -0.48
    ﷺ
    -0.47
     defaultstate
    -0.44
    mester
    -0.43
    WebServlet
    -0.43
     Crusoe
    -0.42
    elemField
    -0.42
     placés
    -0.42
     caneca
    -0.42
    POSITIVE LOGITS
     ReactDOM
    0.43
     المعيارى
    0.43
     oprot
    0.42
    ngdoc
    0.41
     protoimpl
    0.40
    usercontent
    0.40
    adaptiveStyles
    0.40
    inSlope
    0.39
    rrggbb
    0.38
     Interfer
    0.38
    Act Density 1.046%

    No Known Activations