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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and programming constructs involving arrays or lists

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

    LaTeX math mode

    np_acts-logits-general · gemini-2.0-flash

    mathematical indices and code variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :+:
    -0.64
    ilets
    -0.52
    トイレ
    -0.52
     toilet
    -0.52
     Toilet
    -0.50
    Bathroom
    -0.49
     versus
    -0.49
     Bathroom
    -0.48
    mappedBy
    -0.47
    Toilet
    -0.47
    POSITIVE LOGITS
    ScopeManager
    0.61
     فريبيس
    0.60
    ImageContext
    0.58
    endpush
    0.57
    Erreferentziak
    0.55
    meiras
    0.52
    closePath
    0.52
    ształ
    0.52
    astify
    0.51
    ternal
    0.51
    Act Density 0.279%

    No Known Activations