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

    Neuronpedia

    INDEX
    Explanations

    Organizations and proper nouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    سس
    -0.07
    ()])↵
    -0.07
    卉
    -0.07
    ät
    -0.07
    }");
↵
    -0.07
    介
    -0.07
    核心技术
    -0.07
    _principal
    -0.07
    威胁
    -0.07
     ve
    -0.06
    POSITIVE LOGITS
    💘
    0.07
    storybook
    0.06
     overlap
    0.06
    assertEquals
    0.06
    ﹀
    0.06
    paged
    0.06
     לש
    0.06
     BUT
    0.06
    _MULT
    0.06
    上周
    0.06
    Act Density 0.003%

    No Known Activations