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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to characteristics or properties of various subjects

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

    characteristics of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Fordítás
    -0.60
    хьтан
    -0.57
    MLLoader
    -0.56
     Anſ
    -0.52
    chränk
    -0.51
    Personensuche
    -0.51
     Infór
    -0.50
    Iné
    -0.49
    exitRule
    -0.48
    nasium
    -0.48
    POSITIVE LOGITS
     characteristics
    1.00
     Characteristics
    0.86
    characteristics
    0.85
     features
    0.83
     traits
    0.81
    Characteristics
    0.79
     Features
    0.79
     qualities
    0.78
     properties
    0.77
     characteristic
    0.75
    Act Density 0.088%

    No Known Activations