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

    Neuronpedia

    INDEX
    Explanations

    variable declaration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unread
    -0.07
     compare
    -0.07
     lett
    -0.07
    𝇜
    -0.07
    婴幼儿
    -0.07
    鮮
    -0.06
     Swap
    -0.06
     Burgess
    -0.06
    ROP
    -0.06
     caught
    -0.06
    POSITIVE LOGITS
     Obl
    0.07
    科技创新
    0.07
    打球
    0.06
    摆脱
    0.06
    ";
↵
↵
    0.06
    Ark
    0.06
    不克
    0.06
     texto
    0.06
    -hooks
    0.06
     öde
    0.06
    Act Density 0.002%

    No Known Activations