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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistics

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

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.92
    GEBURTSDATUM
    -0.80
    Personendaten
    -0.77
    fromnode
    -0.75
     Мексичка
    -0.73
    ftagPool
    -0.72
     linkovi
    -0.71
    Personensuche
    -0.71
    +#+#
    -0.71
     jspb
    -0.71
    POSITIVE LOGITS
     faible
    0.40
    ╝
    0.37
     faibles
    0.36
    Arrays
    0.35
    Quali
    0.35
     absence
    0.34
     insufficiency
    0.34
     Complete
    0.33
     temporales
    0.32
     low
    0.32
    Act Density 0.057%

    No Known Activations