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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .,
    -0.06
    continent
    -0.06
     between
    -0.06
     Wave
    -0.06
    .animations
    -0.06
    運
    -0.06
    ンピ
    -0.06
    eda
    -0.06
     Streets
    -0.06
     nedeni
    -0.06
    POSITIVE LOGITS
    ilities
    0.06
     Pom
    0.06
     '</
    0.06
     dictatorship
    0.06
    الم
    0.06
    ifers
    0.06
    ๆ
    0.06
     slim
    0.06
     eternal
    0.06
     graf
    0.06
    Act Density 0.113%

    No Known Activations