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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Package
    -0.07
    Chocolate
    -0.07
     Stainless
    -0.07
     increase
    -0.07
     leaks
    -0.06
     servants
    -0.06
     أخرى
    -0.06
     Respond
    -0.06
    Footer
    -0.06
     Tag
    -0.06
    POSITIVE LOGITS
     vliv
    0.06
     коштів
    0.06
     هوش
    0.06
     електрон
    0.06
    �
    0.06
    ReadStream
    0.06
     nějak
    0.06
    	un
    0.06
    '))->
    0.05
    İTESİ
    0.05
    Act Density 0.027%

    No Known Activations