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

    Neuronpedia

    INDEX
    Explanations

    supported documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    屐
    0.47
     спа
    0.47
     свидетель
    0.46
    绉
    0.45
     заб
    0.43
    ‚
    0.43
    后期
    0.42
    軐
    0.42
     любо
    0.42
    ȩ
    0.41
    POSITIVE LOGITS
     paket
    0.49
    korn
    0.44
     nik
    0.43
     prismatic
    0.43
    EDA
    0.42
     geopolitical
    0.42
    EDU
    0.41
     Emotional
    0.41
    gruppen
    0.41
     Sargent
    0.40
    Act Density 0.054%

    No Known Activations