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

    Neuronpedia

    INDEX
    Explanations

    UI code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LEC
    -0.06
    untary
    -0.06
    تماد
    -0.06
    एस
    -0.06
     mtx
    -0.06
     ROCK
    -0.06
     Banana
    -0.06
    Intermediate
    -0.06
    	params
    -0.06
    PREC
    -0.06
    POSITIVE LOGITS
    AYS
    0.07
     DUP
    0.07
    ges
    0.07
    říd
    0.07
    ими
    0.07
    >`↵
    0.07
     boring
    0.06
    าว
    0.06
    ání
    0.06
    ays
    0.06
    Act Density 0.001%

    No Known Activations