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

    Neuronpedia

    INDEX
    Explanations

    references to characters and their relationships in stories

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

    rhetorical devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     faſt
    -0.54
     ſtand
    -0.52
    contentLoaded
    -0.51
    tagHelperRunner
    -0.47
     Ensino
    -0.46
     Chriftian
    -0.45
    -0.44
     ſtill
    -0.43
     deſt
    -0.43
     poffible
    -0.43
    POSITIVE LOGITS
     BoxDecoration
    0.45
     InputDecoration
    0.44
    Diweddarwch
    0.41
     Oran
    0.41
    TokenNameLBRACE
    0.41
    amerikanischer
    0.40
    Typo
    0.39
     sider
    0.38
    obis
    0.38
    dims
    0.37
    Act Density 0.175%

    No Known Activations