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

    Neuronpedia

    INDEX
    Explanations

    mathematics equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     complet
    -0.10
    кі
    -0.08
    ƙ
    -0.08
     geographical
    -0.08
     attaching
    -0.08
    раш
    -0.07
     localização
    -0.07
     geographic
    -0.07
    requirements
    -0.07
     địa
    -0.07
    POSITIVE LOGITS
     alternating
    0.09
     proverb
    0.09
     সির
    0.09
    (GLFW
    0.08
    モデル
    0.08
     altern
    0.08
    タイトル
    0.08
     poslu
    0.08
     Alexandre
    0.08
     gezellige
    0.08
    Act Density 0.010%

    No Known Activations