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

    Neuronpedia

    INDEX
    Explanations

    terms related to system upgrades and transformations

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

    upgrade

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     peł
    -0.50
     miej
    -0.49
     vrijwilli
    -0.47
     wnios
    -0.46
     hvě
    -0.46
     město
    -0.45
     zís
    -0.45
     découv
    -0.44
     ontdek
    -0.44
     aérienne
    -0.44
    POSITIVE LOGITS
    ########.
    0.57
    Parameteri
    0.50
    medriver
    0.49
     patin
    0.49
     DQ
    0.46
    ungeon
    0.45
     Klick
    0.45
    lish
    0.45
    Qw
    0.44
     clique
    0.43
    Act Density 0.210%

    No Known Activations