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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dó
    -0.07
     의해
    -0.06
    era
    -0.06
     Norton
    -0.06
    })(
    -0.06
    ивается
    -0.06
    ียงใหม
    -0.06
    ravel
    -0.06
    ум
    -0.06
    Ef
    -0.06
    POSITIVE LOGITS
    銀
    0.07
     observ
    0.07
     Offering
    0.06
     getState
    0.06
     expenses
    0.06
    _Ref
    0.06
     мин
    0.06
     Ordering
    0.06
     Inline
    0.06
     age
    0.06
    Act Density 0.010%

    No Known Activations