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

    Neuronpedia

    INDEX
    Explanations

    academic or scientific terminology related to mathematics and research

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

    professors and academic titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.56
     propOrder
    -0.52
    parsedMessage
    -0.47
    ésultat
    -0.46
     reactie
    -0.41
     gezet
    -0.41
    buttonShape
    -0.40
     elkaar
    -0.40
     geluid
    -0.40
     materialen
    -0.40
    POSITIVE LOGITS
    centerline
    0.45
     polie
    0.43
    ConstraintMaker
    0.43
    -),
    0.41
    béco
    0.41
    !*\
    0.40
     pelúcia
    0.40
    Memento
    0.40
     INTERESAR
    0.39
     fyr
    0.39
    Act Density 1.914%

    No Known Activations