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

    Neuronpedia

    INDEX
    Explanations

    aspects related to intelligence and integrity in characters

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

    analytical precision and order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ErrIntOverflow
    -0.51
     freely
    -0.46
     estekak
    -0.44
     libremente
    -0.44
     creatively
    -0.43
    adaptiveStyles
    -0.43
     carelessly
    -0.42
     unrestricted
    -0.42
    richTextPanel
    -0.42
     يتيمه
    -0.42
    POSITIVE LOGITS
    ükemmel
    0.47
     methodical
    0.44
    metic
    0.44
     rigid
    0.42
     precision
    0.41
     rigide
    0.41
     orderly
    0.40
     precis
    0.39
     upright
    0.39
    stateProvider
    0.39
    Act Density 0.141%

    No Known Activations