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

    Neuronpedia

    INDEX
    Explanations

    code and instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verlangt
    -0.09
    Ambient
    -0.08
    ерап
    -0.08
     verwerkt
    -0.08
     geregeld
    -0.08
    ախտ
    -0.08
    ئيس
    -0.08
     decir
    -0.08
    (""))
    -0.07
     سياسة
    -0.07
    POSITIVE LOGITS
     foster
    0.08
     pur
    0.08
     estimate
    0.07
     fosters
    0.07
     swap
    0.07
    碼
    0.07
     Bedford
    0.07
     Foster
    0.07
    かわ
    0.07
    ูก
    0.07
    Act Density 0.000%

    No Known Activations