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

    Neuronpedia

    INDEX
    Explanations

    Year

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    avirus
    -0.06
    serialization
    -0.06
     губ
    -0.06
    lambda
    -0.06
     Muk
    -0.06
    (num
    -0.06
     gö
    -0.06
    uada
    -0.06
    мещ
    -0.06
    /****************************************************************************↵
    -0.06
    POSITIVE LOGITS
     Automatic
    0.08
     dryer
    0.08
     compuls
    0.07
     inspiration
    0.07
    �
    0.07
     Compiler
    0.07
    Automatic
    0.07
     gb
    0.06
     Stock
    0.06
    /tty
    0.06
    Act Density 0.003%

    No Known Activations