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

    Neuronpedia

    INDEX
    Explanations

    questions related to reading preferences and experiences

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

    Questions starting with "What" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    favourite things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     señores
    -0.58
    fjspx
    -0.54
    CancelButton
    -0.53
     förstå
    -0.52
    ValueStyle
    -0.49
     explications
    -0.49
     puissiez
    -0.49
     zumal
    -0.48
    存于互联网档案馆
    -0.48
    Tanto
    -0.47
    POSITIVE LOGITS
     favourite
    0.89
     favorite
    0.85
    Favourite
    0.76
     Favourite
    0.76
     Favorite
    0.73
    favourite
    0.71
     funniest
    0.70
    Favorite
    0.70
     fave
    0.69
     happiest
    0.69
    Act Density 0.147%

    No Known Activations