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

    Neuronpedia

    INDEX
    Explanations

    disclaimers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
     فيه
    -0.06
    Shield
    -0.06
    _PACK
    -0.06
    ‌رس
    -0.06
    �
    -0.06
    っぱ
    -0.06
    _wh
    -0.06
    DisplayName
    -0.06
    Eventually
    -0.06
    POSITIVE LOGITS
     cinemas
    0.07
     presenta
    0.07
     reclaim
    0.07
    ROUGH
    0.06
     (--
    0.06
    aji
    0.06
    ırak
    0.06
    UIApplicationDelegate
    0.06
    낸
    0.06
    orphism
    0.06
    Act Density 0.009%

    No Known Activations