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

    Neuronpedia

    INDEX
    Explanations

    elements related to user interface navigation and functionality

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

    <start_of_turn>user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inconnu
    -0.43
     näky
    -0.40
     desconocido
    -0.40
    jelasan
    -0.40
     henkilö
    -0.40
     meisje
    -0.38
     étranger
    -0.38
     Hongrie
    -0.36
     leão
    -0.36
     enfans
    -0.36
    POSITIVE LOGITS
    setDo
    0.65
     defaultstate
    0.63
     للمعارف
    0.60
     мәкал
    0.55
     indoor
    0.54
    IVEREF
    0.53
    httphttps
    0.50
     Ngb
    0.49
    IsContent
    0.49
    indoor
    0.48
    Act Density 0.000%

    No Known Activations