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

    Neuronpedia

    INDEX
    Explanations

    file paths and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sit
    -0.07
     KEEP
    -0.07
     Kirk
    -0.07
    일에
    -0.06
     frees
    -0.06
    .Loader
    -0.06
    COME
    -0.06
     κο
    -0.06
     subtype
    -0.06
     Gall
    -0.06
    POSITIVE LOGITS
    uridad
    0.07
    ibility
    0.07
    manager
    0.07
    asan
    0.07
    esian
    0.06
    ีผ
    0.06
    lict
    0.06
     Manufacturer
    0.06
    ilir
    0.06
    енти
    0.06
    Act Density 0.000%

    No Known Activations