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

    Neuronpedia

    INDEX
    Explanations

    references to specific names and titles in narratives

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

    followed by quotation marks

    np_acts-logits-general · gemini-2.0-flash

    movie and tv show titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.79
     jScrollPane
    -0.77
    findpost
    -0.60
    visiae
    -0.58
    AnchorStyles
    -0.58
    oriam
    -0.57
    idopsis
    -0.54
    viewDidLoad
    -0.54
    SequentialGroup
    -0.54
     useRef
    -0.53
    POSITIVE LOGITS
     whoſe
    0.72
     protoimpl
    0.71
     itſelf
    0.71
     Reſ
    0.69
     Anſ
    0.68
     juſ
    0.68
     reaſon
    0.67
     فريبيس
    0.66
     ſtand
    0.66
     obſ
    0.66
    Act Density 1.379%

    No Known Activations