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

    Neuronpedia

    INDEX
    Explanations

    met

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Partner
    -0.07
    Li
    -0.06
     كيل
    -0.06
    wire
    -0.06
    ۀ
    -0.06
     folks
    -0.06
    เขต
    -0.06
     Yao
    -0.06
    _stub
    -0.06
    ähl
    -0.06
    POSITIVE LOGITS
     purified
    0.06
    _GT
    0.06
     criteria
    0.06
    최고
    0.06
     CURL
    0.06
     Padding
    0.06
     발생
    0.06
     gymn
    0.06
    =bool
    0.06
     fulfilling
    0.06
    Act Density 0.011%

    No Known Activations