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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     ماده
    -0.07
     ออนไลน
    -0.06
    .False
    -0.06
     роботи
    -0.06
    чного
    -0.06
     energies
    -0.06
    -user
    -0.06
    або
    -0.06
     лег
    -0.06
    POSITIVE LOGITS
    */↵↵↵
    0.08
    -marker
    0.07
    mits
    0.06
     ARR
    0.06
    RYPTO
    0.06
    };↵↵↵
    0.06
    Ash
    0.06
     Easy
    0.06
    _GOOD
    0.06
     announces
    0.06
    Act Density 0.001%

    No Known Activations