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

    Neuronpedia

    INDEX
    Explanations

    rankings and metrics related to performance and statistics

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

    rankings and ordinals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    trips
    -0.34
     unterkunft
    -0.33
    IsUnicode
    -0.33
    Источники
    -0.33
     campamento
    -0.32
     directores
    -0.32
    Filmographie
    -0.31
     viajes
    -0.31
     jeunesse
    -0.31
     kolo
    -0.30
    POSITIVE LOGITS
     препратки
    0.58
     الوطنيه
    0.54
    sweise
    0.54
     Савезне
    0.49
     Normdatei
    0.49
    ffine
    0.48
     dezelve
    0.48
    parsedMessage
    0.47
     архивлан
    0.47
    Vidite
    0.47
    Act Density 0.039%

    No Known Activations