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

    Neuronpedia

    INDEX
    Explanations

    expressions related to mental states or perceptions

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

    astonishing, unbelievable, wild, insane

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Démographie
    -0.34
    دانشنامهٔ
    -0.33
     CreateTagHelper
    -0.32
     sweeter
    -0.32
     warn
    -0.31
     rada
    -0.31
     MainAxisSize
    -0.31
     /\.(
    -0.30
    orgung
    -0.29
     poh
    -0.29
    POSITIVE LOGITS
     astounding
    0.85
     astonishing
    0.85
     insane
    0.77
    posterous
    0.77
     unbelievable
    0.77
     bewilder
    0.75
     crazy
    0.74
     incredible
    0.73
     bizarre
    0.73
     Insane
    0.73
    Act Density 0.056%

    No Known Activations