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

    Neuronpedia

    INDEX
    Explanations

    converted

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     abuse
    -0.08
    钋
    -0.08
    少し
    -0.07
    facility
    -0.07
     theatre
    -0.07
     Carlo
    -0.07
    Reservation
    -0.07
     ===>
    -0.07
    alker
    -0.07
     petit
    -0.07
    POSITIVE LOGITS
    民警
    0.07
     البل
    0.07
    GPIO
    0.06
    誤
    0.06
     الصح
    0.06
    OMP
    0.06
    Cog
    0.06
    	GPIO
    0.06
     yı
    0.06
     cog
    0.06
    Act Density 0.024%

    No Known Activations