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

    Neuronpedia

    INDEX
    Explanations

    cities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Indonesia
    -0.06
    oters
    -0.06
     ecology
    -0.06
    Anime
    -0.06
    による
    -0.06
     Elis
    -0.06
     chắn
    -0.06
     обов
    -0.06
    TERNAL
    -0.06
    imbus
    -0.06
    POSITIVE LOGITS
    css
    0.07
     shave
    0.07
    salary
    0.07
    .water
    0.07
     undertaking
    0.06
    gow
    0.06
    ική
    0.06
     Flexible
    0.06
     knowledge
    0.06
    .Deep
    0.06
    Act Density 0.045%

    No Known Activations