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

    Neuronpedia

    INDEX
    Explanations

    programming files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    士
    -0.09
    🎻
    -0.07
     فيه
    -0.07
    聯絡
    -0.07
    סקר
    -0.07
     Loan
    -0.07
    ходить
    -0.07
     SplashScreen
    -0.07
    有所不同
    -0.07
     mater
    -0.07
    POSITIVE LOGITS
     disclosures
    0.08
    _start
    0.08
    Bucket
    0.07
    hammer
    0.07
    \Routing
    0.07
    砘
    0.07
    接力
    0.07
    杆
    0.07
    setattr
    0.07
    /ros
    0.07
    Act Density 0.053%

    No Known Activations