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

    Neuronpedia

    INDEX
    Explanations

    Network statistics and errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    füg
    -0.07
    reply
    -0.07
    فاع
    -0.07
     يول
    -0.06
    	add
    -0.06
    🥖
    -0.06
    Wow
    -0.06
    药物
    -0.06
     Young
    -0.06
    ♾
    -0.06
    POSITIVE LOGITS
     analyzer
    0.08
     нашей
    0.07
    ображен
    0.07
     tightened
    0.07
     لدى
    0.07
     Facial
    0.07
    理发
    0.07
    ставил
    0.07
     HB
    0.07
     поли
    0.07
    Act Density 0.007%

    No Known Activations