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

    Neuronpedia

    INDEX
    Explanations

    suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    济
    -0.07
     operation
    -0.07
    :{}
    -0.07
    181
    -0.07
     groove
    -0.06
     kinetic
    -0.06
     dolphins
    -0.06
    ớt
    -0.06
    olls
    -0.06
    摸
    -0.06
    POSITIVE LOGITS
     clic
    0.06
     شهید
    0.06
     JV
    0.06
     Morales
    0.06
    navbarSupportedContent
    0.06
     Kate
    0.06
     श
    0.06
    ")
↵
    0.06
    usi
    0.06
     Monter
    0.06
    Act Density 0.076%

    No Known Activations