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

    Neuronpedia

    INDEX
    Explanations

    references to comparisons or distinctions between different entities or categories

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

    than any other

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebElementEntity
    -0.54
    mappedBy
    -0.52
    adaptiveStyles
    -0.51
    Autoritní
    -0.50
    Rhestr
    -0.48
     rétro
    -0.45
     suspensión
    -0.45
     gyhoeddwyd
    -0.45
    makeConstraints
    -0.44
    Controllo
    -0.44
    POSITIVE LOGITS
     protoimpl
    0.53
    any
    0.45
     anything
    0.45
    arm
    0.43
     aught
    0.43
    getDoctrine
    0.42
    任何人
    0.41
    ANY
    0.39
    Anything
    0.38
    ereum
    0.38
    Act Density 0.032%

    No Known Activations