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

    Neuronpedia

    INDEX
    Explanations

    UC Berkeley

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Geg
    0.38
     Yangtze
    0.38
     hypoxic
    0.38
     оси
    0.37
     monaster
    0.37
    0.36
     Fos
    0.36
     कथ
    0.35
     く
    0.35
    Hei
    0.35
    POSITIVE LOGITS
    UC
    0.59
     Berkeley
    0.59
    Berkeley
    0.58
     UC
    0.57
     Georgia
    0.57
    Cornell
    0.55
     California
    0.52
     Cornell
    0.52
    Georgia
    0.52
     Stanford
    0.51
    Act Density 0.007%

    No Known Activations