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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and concepts

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

    <start_of_turn>user sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     invokingState
    -0.48
     oposición
    -0.39
    ometrial
    -0.39
     ating
    -0.37
    querque
    -0.36
     uova
    -0.36
     prioritise
    -0.35
     alcanzado
    -0.34
     av
    -0.34
     państw
    -0.34
    POSITIVE LOGITS
    OGND
    0.57
    rungsseite
    0.52
     getView
    0.51
    parsedMessage
    0.51
     للمعارف
    0.50
    IsContent
    0.47
    adaptiveStyles
    0.46
    inSlope
    0.45
    UseVisualStyle
    0.44
    sidemargin
    0.44
    Act Density 0.000%

    No Known Activations