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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    maal
    -0.08
    sha
    -0.07
     newsletter
    -0.07
     extension
    -0.07
    	The
    -0.06
     mã
    -0.06
    циях
    -0.06
    ции
    -0.06
     mej
    -0.06
    (est
    -0.06
    POSITIVE LOGITS
     setAddress
    0.06
     Pasadena
    0.06
     blinking
    0.06
     Unauthorized
    0.06
     careful
    0.06
    witch
    0.06
    ruptcy
    0.06
     Comparative
    0.06
    /delete
    0.06
    386
    0.06
    Act Density 0.006%

    No Known Activations