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

    Neuronpedia

    INDEX
    Explanations

    set theory intervals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jafn
    -0.08
     patience
    -0.07
    -quality
    -0.07
     జగ
    -0.07
     elbow
    -0.07
    _J
    -0.07
     thanks
    -0.07
    ¡
    -0.07
    جه
    -0.07
     J
    -0.07
    POSITIVE LOGITS
     बनाए
    0.09
     deixando
    0.08
     alphabet
    0.08
     abrang
    0.08
     exhaustive
    0.08
     intrusive
    0.08
     Coverage
    0.08
     बनाया
    0.08
     लोगों
    0.08
    .criteria
    0.08
    Act Density 0.020%

    No Known Activations