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

    Neuronpedia

    INDEX
    Explanations

    the names of characters in a story or narrative

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

    Precedes capitalized words/names

    np_acts-logits-general · gemini-2.0-flash

    names that start with a sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KURZBESCHREIBUNG
    -0.51
    FailureListener
    -0.50
    </h2>
    -0.47
     slutt
    -0.45
     Jej
    -0.45
     című
    -0.44
     arrivant
    -0.44
     része
    -0.42
    委員会
    -0.42
     видите
    -0.42
    POSITIVE LOGITS
     himself
    1.23
    himself
    0.96
    SourceChecksum
    0.89
     Himself
    0.87
     ujednoznacz
    0.73
     ***!
    0.72
     그는
    0.72
     الحره
    0.71
    BeginContext
    0.68
    his
    0.66
    Act Density 0.208%

    No Known Activations