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

    Neuronpedia

    INDEX
    Explanations

    authorship information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    그래서
    0.41
     Professors
    0.41
    लिए
    0.40
     говоря
    0.40
     Pergamon
    0.40
    Aprend
    0.40
     Professor
    0.39
    Professor
    0.39
     그래서
    0.39
     रूपा
    0.39
    POSITIVE LOGITS
    r
    0.50
    table
    0.46
     နှစ်
    0.46
     drunkenness
    0.45
     puddle
    0.43
    pt
    0.42
    口座
    0.42
     jail
    0.42
     bubble
    0.41
     tr
    0.41
    Act Density 0.000%

    No Known Activations