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

    Neuronpedia

    INDEX
    Explanations

    IE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =max
    -0.07
     Rash
    -0.06
    rades
    -0.06
    Chars
    -0.06
     Genre
    -0.06
     Mil
    -0.06
    럭
    -0.06
     Translator
    -0.06
    elow
    -0.06
    ظم
    -0.06
    POSITIVE LOGITS
    >

↵
    0.07
    >'↵
    0.07
     guide
    0.07
    -framework
    0.06
     api
    0.06
     //{↵
    0.06
    ">↵
    0.06
     emple
    0.06
    好像
    0.06
     bậc
    0.06
    Act Density 0.000%

    No Known Activations