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

    Neuronpedia

    INDEX
    Explanations

    Fifth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     competency
    -0.07
    Hola
    -0.07
    295
    -0.07
    Money
    -0.07
    těz
    -0.07
    Allen
    -0.07
    795
    -0.07
     upkeep
    -0.06
     interceptor
    -0.06
    ώς
    -0.06
    POSITIVE LOGITS
     Italia
    0.07
     unic
    0.07
     ACE
    0.07
    >Select
    0.06
     refuses
    0.06
     sund
    0.06
     Knock
    0.06
     lasc
    0.06
    (example
    0.06
    .STATUS
    0.06
    Act Density 0.009%

    No Known Activations