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

    Neuronpedia

    INDEX
    Explanations

    q

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    责任
    -0.06
     Mae
    -0.06
     Bar
    -0.06
     kotlinx
    -0.06
     Fus
    -0.06
     när
    -0.06
     Mar
    -0.06
     Hazard
    -0.06
     Honour
    -0.06
     Tax
    -0.06
    POSITIVE LOGITS
     leží
    0.07
     قل
    0.06
     appendString
    0.06
    Quaternion
    0.06
     xếp
    0.06
    UTIL
    0.06
     sice
    0.06
    _)↵
    0.06
     refin
    0.06
    radan
    0.06
    Act Density 0.008%

    No Known Activations