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

    Neuronpedia

    INDEX
    Explanations

    terms related to coding functions and confirmations

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

    confirmation dialogs and pop-ups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.83
     ModelExpression
    -0.77
    CppMethod
    -0.75
     kaarangay
    -0.69
    arraycopy
    -0.68
    sizeCache
    -0.65
    LLocation
    -0.64
    istoitu
    -0.62
     postIndex
    -0.61
    UnusedPrivate
    -0.61
    POSITIVE LOGITS
    swal
    0.94
    sweetalert
    0.90
    Swal
    0.80
     Swal
    0.56
    CancelButton
    0.44
     sweet
    0.40
     déroule
    0.37
    sweet
    0.36
    confirmButton
    0.35
     condam
    0.35
    Act Density 0.000%

    No Known Activations