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

    Neuronpedia

    INDEX
    Explanations

    charset

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     telecommunications
    -0.07
     mineral
    -0.07
    fusion
    -0.07
     malt
    -0.07
     positivity
    -0.07
    毂
    -0.07
    蕊
    -0.06
     supper
    -0.06
     Basket
    -0.06
    iets
    -0.06
    POSITIVE LOGITS
    traî
    0.07
     contrib
    0.07
    ארג
    0.07
     ücretsiz
    0.06
    伤亡
    0.06
    .multiply
    0.06
    0.06
    rolling
    0.06
    样子
    0.06
    0.06
    Act Density 0.001%

    No Known Activations