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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (prefix
    -0.07
     processor
    -0.07
    ██
    -0.07
    تعديل
    -0.07
    (rx
    -0.07
    iddleware
    -0.07
    过度
    -0.07
     תא
    -0.07
    婴幼儿
    -0.07
    也会
    -0.07
    POSITIVE LOGITS
    أهد
    0.07
    kl
    0.07
    ктив
    0.07
    oped
    0.07
    zh
    0.07
     kond
    0.07
    leon
    0.07
     examinations
    0.07
     cured
    0.07
     Routes
    0.06
    Act Density 0.401%

    No Known Activations