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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (section
    -0.07
     filetype
    -0.07
    روه
    -0.06
    (language
    -0.06
    (criteria
    -0.06
    OTP
    -0.06
     Illegal
    -0.06
     있
    -0.06
    休
    -0.06
     veut
    -0.06
    POSITIVE LOGITS
     luxury
    0.06
     attachments
    0.06
    usize
    0.06
     تاریخی
    0.06
     Rochester
    0.06
     respectively
    0.06
    /in
    0.05
     impres
    0.05
     BEST
    0.05
     ساعت
    0.05
    Act Density 0.032%

    No Known Activations