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

    Neuronpedia

    INDEX
    Explanations

    order

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Performance
    -0.07
     Managers
    -0.07
     tijd
    -0.07
    .Helpers
    -0.06
     Wak
    -0.06
    .EntityManager
    -0.06
     Ceramic
    -0.06
     apprentice
    -0.06
     strongest
    -0.06
     Zag
    -0.06
    POSITIVE LOGITS
    .borrow
    0.07
    ARB
    0.06
    ;&#
    0.06
    arma
    0.06
    ANCH
    0.06
    rgb
    0.06
    بالإنجليزية
    0.06
     hPa
    0.06
     postup
    0.06
    ái
    0.06
    Act Density 0.027%

    No Known Activations