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

    Neuronpedia

    INDEX
    Explanations

    references to statistical calculations or metrics, particularly relating to mean values

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

    mean value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Paglinawan
    -0.46
     Chwiliwch
    -0.44
    ricted
    -0.43
    tagHelperRunner
    -0.42
    hopped
    -0.40
    hoes
    -0.39
    peteer
    -0.39
    kira
    -0.39
    utnik
    -0.39
    fortawesome
    -0.38
    POSITIVE LOGITS
    bootstrapcdn
    0.54
    ɵɵ
    0.53
     estekak
    0.51
    省市镇
    0.49
    setMin
    0.48
    middels
    0.47
    complexContent
    0.45
    Mean
    0.44
     Mean
    0.43
    mean
    0.43
    Act Density 0.035%

    No Known Activations