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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or emotional reactions

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

    surprise exclamations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.44
     createSlice
    -0.43
    rungsseite
    -0.39
     تضيفلها
    -0.37
     möchte
    -0.37
     HasFactory
    -0.37
     صوتيه
    -0.36
     Wikimedijinoj
    -0.36
    ConstraintMaker
    -0.35
    enumii
    -0.35
    POSITIVE LOGITS
    Whoa
    1.48
     whoa
    1.36
     Whoa
    1.36
    Woah
    1.26
    woah
    1.11
     wow
    0.71
    Wow
    0.71
    wow
    0.68
     Wow
    0.67
    WOW
    0.65
    Act Density 0.006%

    No Known Activations