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

    Neuronpedia

    INDEX
    Explanations

    code with math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     allocator
    -0.07
     stunt
    -0.07
     건
    -0.07
    _resources
    -0.06
     congen
    -0.06
    /Main
    -0.06
    Installation
    -0.06
     undermined
    -0.06
     Liz
    -0.06
    ulis
    -0.06
    POSITIVE LOGITS
    едини
    0.07
    .rcParams
    0.07
     Girlfriend
    0.06
    energy
    0.06
    ایسه
    0.06
    Cole
    0.06
     hashmap
    0.06
     modifying
    0.06
     використання
    0.06
    اية
    0.06
    Act Density 0.034%

    No Known Activations