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

    Neuronpedia

    INDEX
    Explanations

    the start of a new section or topic in a text

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

    Text preceding question/imperative/colon

    np_acts-logits-general · gemini-2.0-flash

    starts sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Winaray
    -0.64
     intptr
    -0.50
    BeginContext
    -0.50
     Ngb
    -0.49
    SequentialGroup
    -0.49
    )(((
    -0.48
    FECTION
    -0.48
    Референце
    -0.48
     EconPapers
    -0.48
     Infórmanos
    -0.47
    POSITIVE LOGITS
    ConstraintMaker
    0.76
    lgari
    0.63
    évaluateur
    0.62
     виправивши
    0.61
    ArrowToggle
    0.56
    rungsseite
    0.52
    esterno
    0.52
    InjectAttribute
    0.51
    SPATH
    0.51
    Whereas
    0.51
    Act Density 0.194%

    No Known Activations