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

    Neuronpedia

    INDEX
    Explanations

    template and style file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     L
    0.62
     This
    0.59
     The
    0.59
     There
    0.59
     J
    0.55
     More
    0.52
     S
    0.52
     C
    0.51
     A
    0.49
     H
    0.49
    POSITIVE LOGITS
    飜
    0.53
    昻
    0.52
    ントン
    0.52
    ੪
    0.51
    Bsky
    0.50
    翻訳
    0.50
    Arabic
    0.48
    Bowling
    0.48
    integration
    0.48
     stesso
    0.48
    Act Density 0.000%

    No Known Activations