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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or procedural terminology

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

    expressions of faith and commitment to religious principles

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

    various contexts and languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gela
    -0.62
    تقاوى
    -0.58
    цездатний
    -0.56
    PTP
    -0.53
     mitu
    -0.53
     afraid
    -0.50
    ranean
    -0.50
    Precis
    -0.49
     Afraid
    -0.49
     sometimes
    -0.48
    POSITIVE LOGITS
     coscienza
    0.59
    cerely
    0.59
     garanzia
    0.58
    genossen
    0.58
     mijne
    0.57
    談社
    0.56
     amitié
    0.55
     vedea
    0.55
    interopRequire
    0.55
     '\\;'
    0.54
    Act Density 0.191%

    No Known Activations