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

    Neuronpedia

    INDEX
    Explanations

    references to physical objects and their description

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

    fallen or dead things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.46
     Patron
    -0.42
     indul
    -0.40
    patron
    -0.40
     AppModule
    -0.38
     viv
    -0.38
     Paglinawan
    -0.38
    viri
    -0.38
    Patron
    -0.38
    Lesen
    -0.38
    POSITIVE LOGITS
    WireFormatLite
    0.46
     Stücke
    0.44
     zboží
    0.44
     wreckage
    0.43
    dried
    0.40
     døde
    0.39
    ături
    0.39
     pezzi
    0.39
     piese
    0.39
    Cyfeiriadau
    0.39
    Act Density 0.025%

    No Known Activations