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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their representations

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

    Followed by "1.0000" or inside image tags

    np_acts-logits-general · gemini-2.0-flash

    scientific text and plots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tē
    -0.69
     Acton
    -0.62
    '")
    -0.62
    @",
    -0.60
    )"),
    -0.59
     esternos
    -0.59
    zola
    -0.58
    oshin
    -0.58
     ISTAT
    -0.58
    []
    -0.57
    POSITIVE LOGITS
    0
    0.92
     MainAxisSize
    0.70
    umman
    0.60
    prnewswire
    0.55
    rrggbb
    0.54
    ceed
    0.52
    1
    0.51
    __*/
    0.50
    AddTagHelper
    0.50
     Gu
    0.50
    Act Density 0.425%

    No Known Activations