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

    Neuronpedia

    INDEX
    Explanations

    ending

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lists
    -0.07
    лася
    -0.07
     pure
    -0.07
     ذ
    -0.07
     confer
    -0.07
     global
    -0.07
    Browse
    -0.06
     nuova
    -0.06
     Sophie
    -0.06
     своє
    -0.06
    POSITIVE LOGITS
     ending
    0.15
     endings
    0.12
     Ending
    0.11
    -ending
    0.08
    Ending
    0.08
     Gospel
    0.08
    tığını
    0.07
    düğ
    0.07
     extension
    0.07
    entialAction
    0.07
    Act Density 0.003%

    No Known Activations