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

    Neuronpedia

    INDEX
    Explanations

    coding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     film
    -0.08
     arrives
    -0.07
     blended
    -0.07
     exams
    -0.07
    ")));↵
    -0.07
     pred
    -0.07
    technology
    -0.07
    difficulty
    -0.07
     فناوری
    -0.07
     reached
    -0.07
    POSITIVE LOGITS
     fooled
    0.07
    /disc
    0.07
    ByVersion
    0.06
     withRouter
    0.06
     pineapple
    0.06
     personn
    0.06
    σι
    0.06
     �
    0.06
     сайті
    0.06
     eig
    0.05
    Act Density 0.086%

    No Known Activations