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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their formatting, particularly in relation to time and dates

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

    Numbers followed by a dot

    np_acts-logits-general · gemini-2.0-flash

    decimal numbers and versioning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pingback
    -0.56
    ########.
    -0.52
    estras
    -0.51
    发表于
    -0.51
     arşivlendi
    -0.49
    ().__
    -0.49
    vily
    -0.48
    windowFixed
    -0.48
    PreAuthorize
    -0.47
    fromnode
    -0.46
    POSITIVE LOGITS
    ReusableCell
    0.61
    ½
    0.56
     szív
    0.54
     makeStyles
    0.53
     Téléchargez
    0.53
    awaiter
    0.53
    dot
    0.52
     ドット
    0.50
    sprung
    0.50
    XtraGrid
    0.49
    Act Density 0.660%

    No Known Activations