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

    Neuronpedia

    INDEX
    Explanations

    courts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    是不是
    -0.07
    .helper
    -0.07
     beings
    -0.07
    ز
    -0.06
     WON
    -0.06
    coder
    -0.06
     Yog
    -0.06
    凶
    -0.06
    ian
    -0.06
     startX
    -0.06
    POSITIVE LOGITS
    ערות
    0.08
     firestore
    0.07
    ',{↵
    0.07
     reception
    0.07
    骨折
    0.07
    Overflow
    0.07
    落到实处
    0.07
     rua
    0.06
    "\↵
    0.06
    ('./
    0.06
    Act Density 0.013%

    No Known Activations