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

    Neuronpedia

    INDEX
    Explanations

    answering questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cameron
    -0.08
     mít
    -0.07
    ameron
    -0.07
    周收录
    -0.06
     Terminal
    -0.06
    響
    -0.06
     gấp
    -0.06
    Encode
    -0.06
     Место
    -0.06
     Optimization
    -0.06
    POSITIVE LOGITS
    {n
    0.07
    ่อย
    0.06
    はない
    0.06
    uting
    0.06
     學
    0.06
     […]
    0.06
     []),↵
    0.06
    VMLINUX
    0.06
     العربية
    0.06
    нообраз
    0.06
    Act Density 0.029%

    No Known Activations