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
    code
    -0.07
    illin
    -0.07
     Ig
    -0.06
    apeutic
    -0.06
    атег
    -0.06
    िल
    -0.06
    اريخ
    -0.06
    ่นเกม
    -0.06
     بزرگ
    -0.06
    ----</
    -0.06
    POSITIVE LOGITS
    network
    0.07
    奈
    0.07
    *this
    0.07
     capitalize
    0.06
     있을
    0.06
     Derived
    0.06
     ribbon
    0.06
     DataContext
    0.06
     optimizations
    0.06
     seek
    0.06
    Act Density 0.058%

    No Known Activations