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

    Neuronpedia

    INDEX
    Explanations

    Places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    коз
    -0.07
     enabling
    -0.06
    く
    -0.06
    William
    -0.06
     Based
    -0.06
    -des
    -0.06
     имени
    -0.06
     exhibiting
    -0.06
     nuclear
    -0.06
     MU
    -0.06
    POSITIVE LOGITS
    foo
    0.06
    čních
    0.06
    ";↵↵↵
    0.06
    Neighbors
    0.06
    .quiz
    0.06
     EP
    0.06
     foo
    0.06
     POSIX
    0.06
    ávací
    0.06
     dnes
    0.06
    Act Density 0.064%

    No Known Activations