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

    Neuronpedia

    INDEX
    Explanations

    programming or markup elements and their attributes

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

    Characters used in number formatting

    np_acts-logits-general · gemini-2.0-flash

    localization formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defStyle
    -0.65
     defStyleAttr
    -0.59
    hematical
    -0.59
    posedge
    -0.59
    BoxShadow
    -0.58
    phazard
    -0.58
     getCity
    -0.57
    ginine
    -0.56
    onAttach
    -0.56
    ouser
    -0.54
    POSITIVE LOGITS
     %
    0.66
    (%
    0.57
    ,%
    0.55
    TextLabel
    0.55
    %
    0.55
    source
    0.54
    }}%
    0.53
     }}"
    0.53
    aarrggbb
    0.53
     (%
    0.53
    Act Density 0.105%

    No Known Activations