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

    Neuronpedia

    INDEX
    Explanations

    technical terms and properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aster
    0.44
    Successful
    0.43
     follicles
    0.43
    0.43
    ជាមួយនឹង
    0.42
     wagons
    0.41
    system
    0.40
     ethan
    0.40
    successfully
    0.40
     olas
    0.40
    POSITIVE LOGITS
    ógio
    0.53
    ércio
    0.49
     revêt
    0.48
    ísmo
    0.45
    érêt
    0.45
    レール
    0.44
     મુ
    0.44
    ิตย์
    0.44
    ﺄ
    0.44
     書い
    0.44
    Act Density 0.004%

    No Known Activations