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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ehicle
    -0.07
    	opt
    -0.06
    ière
    -0.06
    .Func
    -0.06
    мит
    -0.06
    xab
    -0.06
    UL
    -0.06
    (T
    -0.06
    +B
    -0.06
    Ale
    -0.06
    POSITIVE LOGITS
    層
    0.08
     �
    0.07
    儀
    0.07
    -backed
    0.07
    ":"","
    0.07
    ограм
    0.07
    /vendors
    0.07
    未
    0.07
     Vend
    0.06
    36
    0.06
    Act Density 0.011%

    No Known Activations