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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     정책
    -0.07
    BS
    -0.07
    ية
    -0.06
     appropriations
    -0.06
    ignty
    -0.06
    ubishi
    -0.06
    _strike
    -0.06
    ScrollView
    -0.06
    .BorderSide
    -0.06
    ยน
    -0.06
    POSITIVE LOGITS
    Axes
    0.07
     filenames
    0.07
    =↵↵
    0.07
    055
    0.07
    ricane
    0.06
    ↵            ↵
    0.06
     Julie
    0.06
    /ms
    0.06
     celle
    0.06
    Amy
    0.06
    Act Density 0.000%

    No Known Activations