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

    Neuronpedia

    INDEX
    Explanations

    helpful

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Worce
    -0.07
     Mandatory
    -0.07
    щини
    -0.07
    وی
    -0.06
     Voc
    -0.06
     disregard
    -0.06
    -------↵↵
    -0.06
    CE
    -0.06
     execution
    -0.06
    انی
    -0.06
    POSITIVE LOGITS
     Gratis
    0.07
     bj
    0.07
     Shops
    0.07
     strategies
    0.07
    ีก
    0.07
    	mc
    0.07
    Han
    0.07
     applauded
    0.06
    >New
    0.06
    생
    0.06
    Act Density 0.009%

    No Known Activations