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

    Neuronpedia

    INDEX
    Explanations

    was were

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	memcpy
    -0.08
     PackageManager
    -0.06
     arrest
    -0.06
    考え
    -0.06
     //
↵
    -0.06
     postData
    -0.06
     arrests
    -0.06
     AMD
    -0.06
     graduates
    -0.06
     chipset
    -0.06
    POSITIVE LOGITS
     norms
    0.07
    _warning
    0.07
     yö
    0.06
    Sarah
    0.06
     kao
    0.06
    explode
    0.06
     through
    0.06
     pró
    0.06
     lust
    0.06
    -й
    0.06
    Act Density 0.043%

    No Known Activations