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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "on"

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

    months and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſche
    -0.59
     ostavi
    -0.56
     Majefty
    -0.48
     pleaſure
    -0.48
    ChildScrollView
    -0.47
    ſelves
    -0.46
     ſp
    -0.44
    ſelf
    -0.43
     Reſ
    -0.43
     raiſ
    -0.43
    POSITIVE LOGITS
     للمعارف
    0.60
     August
    0.52
     October
    0.52
    BASELINE
    0.52
    enumi
    0.50
     February
    0.50
     Aug
    0.49
    GOTREF
    0.49
     September
    0.49
     December
    0.49
    Act Density 0.001%

    No Known Activations