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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deutsche
    -0.07
    ela
    -0.07
     weir
    -0.07
    iginal
    -0.06
     moderne
    -0.06
     Publisher
    -0.06
    ’deki
    -0.06
    .gen
    -0.06
    пр
    -0.06
    celain
    -0.06
    POSITIVE LOGITS
    rze
    0.07
     SITE
    0.06
     UIViewController
    0.06
     collaborative
    0.06
     góc
    0.06
     Ble
    0.06
     nth
    0.06
    htable
    0.06
     certs
    0.06
    Aut
    0.06
    Act Density 0.056%

    No Known Activations