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

    Neuronpedia

    INDEX
    Explanations

    phrases related to numerical calculations and data analysis

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

    calculated values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelf
    -0.48
     itſelf
    -0.45
    KommentareTeilen
    -0.43
     RIPRODUZIONE
    -0.43
    WithIOException
    -0.42
     defStyleAttr
    -0.42
     IFTTT
    -0.42
    pois
    -0.42
     pleaſure
    -0.41
    lovakia
    -0.40
    POSITIVE LOGITS
     calculated
    1.52
     computed
    1.43
    calculated
    1.39
     Calculated
    1.38
    Calculated
    1.37
    computed
    1.24
     Computed
    1.18
    Computed
    1.16
     predicted
    0.99
    predicted
    0.91
    Act Density 0.051%

    No Known Activations