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

    Neuronpedia

    INDEX
    Explanations

    words related to processes, conditions, and states that indicate progress or improvement

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

    Text following questions marked by "Q:"

    np_acts-logits-general · gemini-2.0-flash

    technical descriptions and specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.84
    Personendaten
    -0.72
    räck
    -0.69
    MigrationBuilder
    -0.68
    "]="
    -0.67
     galore
    -0.62
    DockStyle
    -0.61
    __":
    -0.60
     defaultstate
    -0.60
     quoque
    -0.58
    POSITIVE LOGITS
    WebServlet
    0.54
    ródło
    0.50
    ViewImports
    0.50
     насељу
    0.49
    HasAnnotation
    0.49
    saraba
    0.48
     when
    0.48
     recommandée
    0.48
    aktery
    0.47
     للغاية
    0.47
    Act Density 0.758%

    No Known Activations