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

    Neuronpedia

    INDEX
    Explanations

    indicators of user input or response options in a dialogue context

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

    'Y' followed by symbols and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.42
    ])]
    -0.42
    intios
    -0.38
    StrictEqual
    -0.38
     engine
    -0.38
     Ausbau
    -0.38
    院
    -0.37
    AccessorTable
    -0.37
     reklam
    -0.36
    andy
    -0.36
    POSITIVE LOGITS
     المعيارى
    0.66
     otomatig
    0.50
    Билгалдахарш
    0.44
     getchar
    0.44
    ########.
    0.44
    RTEX
    0.44
    createClass
    0.43
    Personendaten
    0.42
     Савезне
    0.42
     kasarigan
    0.41
    Act Density 0.080%

    No Known Activations