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

    Neuronpedia

    INDEX
    Explanations

    references to legal procedures and documentation

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

    "the" followed by a fact-related word

    np_acts-logits-general · gemini-2.0-flash

    determinist fact-based terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -0.87
    ponses
    -0.66
    oredCriteria
    -0.63
    :✨
    -0.61
    liothèque
    -0.61
     AssemblyVersion
    -0.60
     createSlice
    -0.59
     useRef
    -0.55
    djangoproject
    -0.54
    gonic
    -0.54
    POSITIVE LOGITS
     factual
    0.66
    ädie
    0.56
     facts
    0.56
    躇
    0.53
     instant
    0.52
     fact
    0.51
     competing
    0.51
    tual
    0.50
     finding
    0.47
     nature
    0.47
    Act Density 1.819%

    No Known Activations