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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bearing
    -0.07
    	continue
    -0.07
     보내
    -0.06
    ynamodb
    -0.06
    liste
    -0.06
     Login
    -0.06
     množ
    -0.06
     Delivery
    -0.06
     honour
    -0.06
     debates
    -0.06
    POSITIVE LOGITS
    الله
    0.07
    median
    0.07
    iếng
    0.07
     getDefault
    0.07
     února
    0.07
     srdce
    0.07
    _USB
    0.07
     SZ
    0.06
    =[],
    0.06
    _strcmp
    0.06
    Act Density 0.001%

    No Known Activations