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

    Neuronpedia

    INDEX
    Explanations

    css declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Fantasy
    0.42
    Basic
    0.38
    sk
    0.37
     Fantasy
    0.36
    LayoutParams
    0.35
    asons
    0.34
     ')')
    0.34
    Children
    0.34
    acies
    0.34
     Bounty
    0.34
    POSITIVE LOGITS
     fluctuation
    0.41
     Vernon
    0.39
    模
    0.39
     chegou
    0.38
     cryptography
    0.38
    پیش
    0.38
     نموذج
    0.38
     توقع
    0.37
    ابا
    0.37
     erwartet
    0.37
    Act Density 0.001%

    No Known Activations