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

    Neuronpedia

    INDEX
    Explanations

    Representative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    　　　　　　　　　　　
    -0.08
    Manufacturer
    -0.07
    nonnull
    -0.07
    ?“↵↵
    -0.07
     Weekend
    -0.07
    ku
    -0.06
     adulti
    -0.06
    	y
    -0.06
     succès
    -0.06
    _JOB
    -0.06
    POSITIVE LOGITS
     Rep
    0.08
     Sen
    0.07
    Reach
    0.07
     Sergei
    0.07
    Sen
    0.06
    мо
    0.06
     Jacqueline
    0.06
    епти
    0.06
     redefine
    0.06
    Rep
    0.06
    Act Density 0.004%

    No Known Activations