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

    Neuronpedia

    INDEX
    Explanations

    filter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    瑰
    -0.08
    缞
    -0.08
     fend
    -0.08
     nowrap
    -0.07
    特色小镇
    -0.07
     imageNamed
    -0.07
    硔
    -0.07
    嵝
    -0.07
    ixels
    -0.07
    traditional
    -0.07
    POSITIVE LOGITS
    ♡
    0.08
    Mil
    0.07
    Coal
    0.07
     intimidation
    0.07
    Mapper
    0.07
     Et
    0.06
     quarantine
    0.06
    💔
    0.06
     Wit
    0.06
     العسكرية
    0.06
    Act Density 0.009%

    No Known Activations