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

    Neuronpedia

    INDEX
    Explanations

    Moj

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -specific
    -0.06
     consts
    -0.06
    ystery
    -0.06
     getaway
    -0.06
    $page
    -0.06
    Sat
    -0.06
     έως
    -0.06
     especific
    -0.05
     preço
    -0.05
     markings
    -0.05
    POSITIVE LOGITS
     奥
    0.08
     Amir
    0.07
     MAV
    0.07
     ale
    0.07
     Comcast
    0.07
    並
    0.06
     forty
    0.06
    '){↵
    0.06
     of
    0.06
     abilities
    0.06
    Act Density 0.033%

    No Known Activations