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

    Neuronpedia

    INDEX
    Explanations

    patterns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     отмеч
    -0.07
     고려
    -0.06
     див
    -0.06
     ensure
    -0.06
    _literal
    -0.06
    _PACK
    -0.06
     هیچ
    -0.06
    ุตสาห
    -0.06
    enth
    -0.06
     провод
    -0.06
    POSITIVE LOGITS
     honored
    0.07
     Liberation
    0.07
     noir
    0.06
    Scroll
    0.06
     Lecture
    0.06
    seven
    0.06
     paintings
    0.06
     NAMES
    0.06
     registrar
    0.06
    .scroll
    0.06
    Act Density 0.015%

    No Known Activations