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

    Neuronpedia

    INDEX
    Explanations

    sections of text that are visually separated or marked, often indicating an important format or transition

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

    company names and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    7
    -0.63
    trell
    -0.43
     seventy
    -0.43
    ppell
    -0.41
    ulemon
    -0.41
    usercontent
    -0.40
     Tremb
    -0.40
    ۷
    -0.40
    venty
    -0.40
    utz
    -0.39
    POSITIVE LOGITS
    ítmény
    0.66
    ******
    0.66
    ------
    0.65
    ing
    0.63
     stället
    0.59
    BeginContext
    0.59
    SOUNDBITE
    0.58
    談社
    0.58
    Smartphone
    0.56
    Liga
    0.56
    Act Density 0.041%

    No Known Activations