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

    Neuronpedia

    INDEX
    Explanations

    preferences and actions related to managing content collections

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

    Chinese text and translations

    np_acts-logits-general · gemini-2.0-flash

    media states: watching, watched, unfinished, available

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.66
     ſtate
    -0.62
     ſtre
    -0.60
     houſe
    -0.55
     pleaſure
    -0.55
     uſed
    -0.54
     fubject
    -0.54
     diſt
    -0.52
     paſſ
    -0.52
     ſub
    -0.52
    POSITIVE LOGITS
     незавершена
    0.61
    principalColumn
    0.61
     BoxDecoration
    0.56
    ﹧
    0.56
    tôi
    0.55
     photolibrary
    0.54
    ziasztok
    0.54
    gså
    0.52
    0.51
    cửa
    0.50
    Act Density 0.077%

    No Known Activations