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

    Neuronpedia

    INDEX
    Explanations

    network configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    骸
    -0.07
    蹴
    -0.07
     sang
    -0.07
     المياه
    -0.07
    钢材
    -0.06
    下发
    -0.06
    �
    -0.06
    改良
    -0.06
    法案
    -0.06
    ⾦
    -0.06
    POSITIVE LOGITS
     patiently
    0.07
    alta
    0.07
     caregivers
    0.07
     güc
    0.07
     INTO
    0.07
    _const
    0.07
    ꞊
    0.07
    ardless
    0.07
    )),
↵
    0.07
     distributed
    0.07
    Act Density 0.017%

    No Known Activations