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

    Neuronpedia

    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    awr
    -0.09
    醒
    -0.08
     proclamation
    -0.08
    ‼
    -0.08
     Reflection
    -0.07
     Pads
    -0.07
     HUGE
    -0.07
     Easily
    -0.07
     Choose
    -0.07
    ères
    -0.07
    POSITIVE LOGITS
     studies
    0.13
     papers
    0.13
    Studies
    0.11
     topics
    0.11
     Papers
    0.10
     अध्य
    0.10
     ಸಾಹಿತ್ಯ
    0.10
    papers
    0.09
     literature
    0.09
     journals
    0.09
    Act Density 0.054%

    No Known Activations