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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming code structure and syntax

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

    Hexadecimal numbers

    np_acts-logits-general · gemini-2.0-flash

    terminal output and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dialog
    -0.57
    Dialog
    -0.54
     road
    -0.53
     disambiguazione
    -0.53
     clicked
    -0.52
    artney
    -0.51
     dialog
    -0.51
     löyty
    -0.50
    road
    -0.49
     dialogue
    -0.49
    POSITIVE LOGITS
    urses
    0.66
    ミナル
    0.62
     terminal
    0.59
    COLORS
    0.57
    终端
    0.55
    Diweddarwch
    0.54
    Terminal
    0.54
    terminal
    0.54
     Terminal
    0.53
     Coloured
    0.53
    Act Density 0.787%

    No Known Activations