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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ische
    -0.08
    улю
    -0.07
    ophage
    -0.06
     Buzz
    -0.06
     sequential
    -0.06
    Ian
    -0.06
    orgeous
    -0.06
    钮
    -0.06
    istically
    -0.06
    wd
    -0.06
    POSITIVE LOGITS
    #endif
    0.07
    ++++++++++++++++
    0.07
    يس
    0.07
    /blog
    0.07
     н
    0.07
     denim
    0.07
    健康
    0.06
    masının
    0.06
    memory
    0.06
    :Is
    0.06
    Act Density 0.000%

    No Known Activations