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

    Neuronpedia

    INDEX
    Explanations

    references to changes in quantities or measurements

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

    followed by "from" or "to"

    np_acts-logits-general · gemini-2.0-flash

    from X to Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wohl
    -0.46
    PARATOR
    -0.45
    振
    -0.42
     dif
    -0.42
     Rah
    -0.42
    centiles
    -0.41
     excels
    -0.41
    gga
    -0.39
    utnik
    -0.39
    ই
    -0.39
    POSITIVE LOGITS
     from
    1.00
     to
    0.95
    VersionUID
    0.86
    windowFixed
    0.82
    TagHelper
    0.81
     <<<<<<<<<<<<<<
    0.80
     från
    0.79
    至
    0.78
    from
    0.78
     menjadi
    0.73
    Act Density 0.478%

    No Known Activations