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

    Neuronpedia

    INDEX
    Explanations

    keyboard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    بح
    -0.08
     Engineers
    -0.07
    ortex
    -0.07
    -bre
    -0.07
    -Muslim
    -0.07
    -cur
    -0.07
    _prime
    -0.07
     steep
    -0.06
    875
    -0.06
    uffman
    -0.06
    POSITIVE LOGITS
     activate
    0.07
    â
    0.06
    �
    0.06
    htmlspecialchars
    0.06
     priorit
    0.06
     звіт
    0.06
     swap
    0.06
    ो,
    0.06
     دانلود
    0.06
    cl
    0.06
    Act Density 0.009%

    No Known Activations