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

    Neuronpedia

    INDEX
    Explanations

    exclamation marks and expressions of excitement or surprise

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

    emphatic endings and greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mær
    -0.42
    hæng
    -0.39
     avoient
    -0.39
     inconnu
    -0.39
    AccessorTable
    -0.38
    geführten
    -0.35
    adaptiveStyles
    -0.35
    XMLSchema
    -0.34
     recevrez
    -0.34
     prendra
    -0.33
    POSITIVE LOGITS
    !,
    0.63
    !;
    0.63
     Aniston
    0.60
     Ababa
    0.59
     Assisi
    0.57
    riwal
    0.56
    styleUrls
    0.56
    tvguidetime
    0.55
    !.
    0.54
    timewa
    0.53
    Act Density 0.033%

    No Known Activations