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

    Neuronpedia

    INDEX
    Explanations

    research studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iliki
    -0.07
     Guardians
    -0.07
     ifstream
    -0.07
     discret
    -0.07
    ERE
    -0.07
    acht
    -0.07
     Rus
    -0.07
    查看
    -0.07
    .exceptions
    -0.06
    -images
    -0.06
    POSITIVE LOGITS
    两
    0.07
    thè
    0.07
    \Plugin
    0.07
    Prime
    0.06
    뭏
    0.06
    مز
    0.06
    晫
    0.06
    以人为
    0.06
    꽹
    0.06
    
    0.06
    Act Density 0.030%

    No Known Activations