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

    Neuronpedia

    INDEX
    Explanations

    instances of demonstrated efficacy and effectiveness in clinical or experimental contexts

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

    "showed" followed by positive attributes

    np_acts-logits-general · gemini-2.0-flash

    shows degree of outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.77
     proprement
    -0.67
    guien
    -0.64
    ۜ
    -0.60
    ValueStyle
    -0.59
    something
    -0.58
    Nothing
    -0.57
    Something
    -0.56
     SOMETHING
    -0.56
    NOTHING
    -0.56
    POSITIVE LOGITS
     excellent
    1.34
     good
    1.22
     satisfactory
    1.05
    excellent
    1.05
     significant
    1.04
     high
    1.03
     considerable
    1.01
     remarkable
    1.00
     substantial
    0.98
     negligible
    0.97
    Act Density 1.648%

    No Known Activations