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

    Neuronpedia

    INDEX
    Explanations

    significant punctuation and formatting elements in the text

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

    novel concepts and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kegaard
    -0.57
     ब्रेकडाउन
    -0.44
    ulemon
    -0.42
    참고
    -0.42
    Попис
    -0.41
    一応
    -0.41
     permanentes
    -0.41
    PrototypeOf
    -0.41
     poveznice
    -0.40
     peor
    -0.40
    POSITIVE LOGITS
     thrilling
    0.47
     captivating
    0.46
     surprising
    0.44
     revealing
    0.44
     dynamic
    0.42
    acidad
    0.42
     captivated
    0.41
    yonel
    0.41
     effortlessly
    0.41
     intriguing
    0.40
    Act Density 0.001%

    No Known Activations