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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     JK
    -0.08
    消息称
    -0.08
    Fd
    -0.07
    _id
    -0.07
     stressing
    -0.06
     concession
    -0.06
     k
    -0.06
     danced
    -0.06
    PROGRAM
    -0.06
    옏
    -0.06
    POSITIVE LOGITS
    allee
    0.08
    eties
    0.08
    た
    0.07
    🐠
    0.07
    ReturnType
    0.07
     ${↵
    0.07
    荑
    0.07
     seguir
    0.07
     Renderer
    0.07
    污泥
    0.07
    Act Density 0.013%

    No Known Activations