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

    Neuronpedia

    INDEX
    Explanations

    references to various effects or impacts in scientific contexts

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

    describing results and influences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    chengladbach
    -0.55
    +#+#
    -0.54
     carpenters
    -0.51
    ChildScrollView
    -0.48
     astronomers
    -0.47
     jongen
    -0.47
    inatal
    -0.47
     Anthropological
    -0.47
     Latimer
    -0.47
     Astronomical
    -0.46
    POSITIVE LOGITS
     effect
    1.91
    effect
    1.80
     Effect
    1.69
    Effect
    1.68
     effects
    1.54
     EFFECT
    1.45
    effects
    1.40
     Effects
    1.34
    Effects
    1.31
    ffect
    1.30
    Act Density 0.049%

    No Known Activations