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

    Neuronpedia

    INDEX
    Explanations

    Scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ्ल
    -0.07
    des
    -0.06
    čit
    -0.06
     日本
    -0.06
     ガ
    -0.06
    logic
    -0.06
    pur
    -0.06
     �
    -0.06
     comunidad
    -0.06
    wood
    -0.06
    POSITIVE LOGITS
    جميع
    0.06
     сопров
    0.06
     humano
    0.06
    \r
    0.06
     Země
    0.06
     bestselling
    0.06
    assertTrue
    0.06
     destination
    0.06
    (TreeNode
    0.06
    操作
    0.06
    Act Density 0.030%

    No Known Activations