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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and functions related to user interactions

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

    invert, toggle, flip

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TableBody
    -0.35
     podí
    -0.34
     Тем
    -0.34
    postmedia
    -0.33
    jsxFileName
    -0.30
    couverte
    -0.30
    contact
    -0.30
    MarshalTo
    -0.29
    XMLSchema
    -0.29
     VIDEOTAPE
    -0.29
    POSITIVE LOGITS
     invert
    1.04
     toggle
    0.90
     flip
    0.87
     inversion
    0.86
     inver
    0.83
     togg
    0.82
     flipping
    0.81
     reversal
    0.81
     Toggle
    0.81
    invert
    0.80
    Act Density 0.166%

    No Known Activations