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

    Neuronpedia

    INDEX
    Explanations

    references and citations for academic publications

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

    scientific publications

    np_acts-logits-general · gemini-2.0-flash

    journal names after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagext
    -0.63
     "..\..\..\
    -0.55
    perg
    -0.54
    ThroughAttribute
    -0.53
    :✨
    -0.52
    RTLD
    -0.50
    enuta
    -0.49
    RectangleBorder
    -0.49
    resave
    -0.48
     bort
    -0.48
    POSITIVE LOGITS
     Nature
    0.93
    Nature
    0.88
     nature
    0.87
    nature
    0.84
     NATURE
    0.81
    NATURE
    0.74
     natures
    0.70
     Science
    0.70
    Science
    0.67
     Cæsar
    0.66
    Act Density 0.747%

    No Known Activations