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

    Neuronpedia

    INDEX
    Explanations

    he

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Atoms
    -0.07
     plt
    -0.07
     EI
    -0.07
    justice
    -0.07
    UME
    -0.06
     Stanford
    -0.06
    ्टम
    -0.06
    阅
    -0.06
    毕业
    -0.06
    ICS
    -0.06
    POSITIVE LOGITS
    -Th
    0.07
    �
    0.07
    \Helpers
    0.07
     BDS
    0.07
     destined
    0.06
    .magic
    0.06
    ++↵↵
    0.06
     =$
    0.06
     mezi
    0.06
     пак
    0.06
    Act Density 0.129%

    No Known Activations