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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    secret
    -0.07
    ผสม
    -0.07
    _FULLSCREEN
    -0.07
    _playlist
    -0.07
     Gluten
    -0.07
    人权
    -0.06
     sürü
    -0.06
    🛁
    -0.06
    \Input
    -0.06
    -driver
    -0.06
    POSITIVE LOGITS
     חברת
    0.08
     هذا
    0.07
    郑
    0.07
     relinqu
    0.07
    arks
    0.07
    	if
    0.07
    czy
    0.07
    ग
    0.07
    oyo
    0.07
    馬
    0.07
    Act Density 0.001%

    No Known Activations