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

    Neuronpedia

    INDEX
    Explanations

    references to toolbars or related interface components in software

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

    toolbar and bars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    -0.36
     Sime
    -0.32
     Argentine
    -0.32
    енье
    -0.31
    StrictEqual
    -0.31
    き
    -0.30
     Bos
    -0.30
    <em>
    -0.29
     tip
    -0.29
    KommentareTeilen
    -0.28
    POSITIVE LOGITS
     toolbar
    2.41
     Toolbar
    2.05
    toolbar
    2.00
    Toolbar
    1.53
    ToolBar
    1.40
    TOOLBAR
    1.34
    toolBar
    1.07
     taskbar
    0.93
    bars
    0.87
     StringTokenizer
    0.86
    Act Density 0.001%

    No Known Activations