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

    Neuronpedia

    INDEX
    Explanations

    Republican, Protestant, English, Independent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ybės
    0.54
    ertype
    0.53
    Compliance
    0.52
    ностью
    0.51
    ಿಸ್ಟ
    0.51
     circunferência
    0.51
    compliance
    0.50
    FragmentManager
    0.49
    梵
    0.49
    nunique
    0.49
    POSITIVE LOGITS
    !
    0.47
     sewing
    0.46
     later
    0.45
     cloth
    0.45
     ankle
    0.43
     creep
    0.42
     insects
    0.41
     '
    0.41
     margine
    0.41
     雪
    0.40
    Act Density 0.001%

    No Known Activations