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

    Neuronpedia

    INDEX
    Explanations

    expressions of duality or choice between options

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

    one way or another

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.63
    uxxxx
    -0.56
    +:+
    -0.52
    VideoCapture
    -0.49
    +#+#
    -0.49
    OGND
    -0.48
    BeginContext
    -0.46
    findpost
    -0.46
    Gambas
    -0.46
     Normdatei
    -0.45
    POSITIVE LOGITS
     way
    2.70
    way
    1.77
     WAY
    1.76
    Way
    1.73
     Way
    1.64
    WAY
    1.52
     ways
    1.41
     façon
    1.36
     manera
    1.35
     manière
    1.29
    Act Density 0.051%

    No Known Activations