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

    Neuronpedia

    INDEX
    Explanations

    broad statements about inclusivity and comprehensive offerings

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

    everything in features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    цездатний
    -0.69
     myſelf
    -0.60
    sizeCache
    -0.59
    Personendaten
    -0.56
     Wicidata
    -0.55
     Савезне
    -0.52
    Халык
    -0.52
     consuma
    -0.51
     Administrativna
    -0.51
     المعيارى
    -0.50
    POSITIVE LOGITS
     features
    0.47
     Features
    0.43
    features
    0.41
     diversité
    0.40
     FEATURES
    0.39
    Features
    0.36
     Merkmale
    0.36
    醐
    0.36
     atractivos
    0.36
     feature
    0.35
    Act Density 0.168%

    No Known Activations