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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .sh
    -0.07
     counterfeit
    -0.07
     estão
    -0.06
    jl
    -0.06
    терн
    -0.06
     kå
    -0.06
    unset
    -0.06
    moil
    -0.06
    	RT
    -0.06
    앙
    -0.06
    POSITIVE LOGITS
     Grinding
    0.08
     Organic
    0.06
     Hill
    0.06
    iological
    0.06
     Randall
    0.06
     сох
    0.06
     gravid
    0.06
     Sheridan
    0.06
     Dys
    0.06
     serg
    0.06
    Act Density 0.023%

    No Known Activations