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

    Neuronpedia

    INDEX
    Explanations

    Code build processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     influ
    -0.07
    -online
    -0.07
    \data
    -0.06
     Только
    -0.06
     Quran
    -0.06
     parts
    -0.06
    _Post
    -0.06
     llegar
    -0.06
     flea
    -0.06
     shining
    -0.06
    POSITIVE LOGITS
     اند
    0.07
    }}↵↵
    0.07
     ヾ
    0.06
     د
    0.06
    HUD
    0.06
    ่าจะ
    0.06
    ãeste
    0.06
     національ
    0.06
    评价
    0.06
    449
    0.06
    Act Density 0.001%

    No Known Activations