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

    Neuronpedia

    INDEX
    Explanations

    uncertain phrases or statements about knowledge, understanding, or clarity

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

    Expressing uncertainty or lack of knowledge

    np_acts-logits-general · gemini-2.0-flash

    questions about unknowns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.60
    antMatchers
    -0.57
     SafeMath
    -0.57
    NavLink
    -0.55
    stdafx
    -0.54
    +:+
    -0.54
    RunWith
    -0.51
    cookieParser
    -0.49
    Rè
    -0.48
     akad
    -0.47
    POSITIVE LOGITS
     unknown
    2.43
     Unknown
    2.10
    unknown
    2.08
     unknowns
    1.97
    Unknown
    1.94
     unclear
    1.87
     uncertain
    1.82
     UNKNOWN
    1.80
     неизвест
    1.77
     unsure
    1.76
    Act Density 0.720%

    No Known Activations