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

    Neuronpedia

    INDEX
    Explanations

    instances of code editing commands and options

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

    DO NOT EDIT, PositiveButton

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.42
    setVerticalGroup
    -0.41
     cassette
    -0.40
     sails
    -0.40
     Quartz
    -0.39
     synag
    -0.39
    BagLayout
    -0.39
     remb
    -0.39
     tombe
    -0.39
    ffiche
    -0.39
    POSITIVE LOGITS
    PositiveButton
    0.61
     Infórmanos
    0.54
    تقاوى
    0.54
    AnchorStyles
    0.53
     nahilalakip
    0.52
    DockStyle
    0.52
     ProtoMessage
    0.51
     dAtA
    0.50
     ExecuteAsync
    0.49
     فريبيس
    0.49
    Act Density 0.001%

    No Known Activations