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

    Neuronpedia

    INDEX
    Explanations

    references to global or widespread contexts

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

    global reach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    findpost
    -0.62
    aarrggbb
    -0.49
    SequentialGroup
    -0.44
     además
    -0.42
    UnusedPrivate
    -0.41
    -0.41
    Ƚ
    -0.41
    textview
    -0.40
    URLException
    -0.40
     dere
    -0.39
    POSITIVE LOGITS
     worldwide
    0.77
     across
    0.69
     throughout
    0.67
     everywhere
    0.64
     khắp
    0.63
     globally
    0.61
     global
    0.59
    worldwide
    0.59
    throughout
    0.55
    zbęd
    0.55
    Act Density 0.014%

    No Known Activations