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

    Neuronpedia

    INDEX
    Explanations

    describing states or roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lounges
    0.49
    癥
    0.48
     grupo
    0.48
    ាតុ
    0.47
    ن
    0.45
    Dropdown
    0.43
     personaggio
    0.43
    ൭
    0.43
     lounging
    0.43
    របស់អ្នក
    0.42
    POSITIVE LOGITS
    ર
    0.54
     ns
    0.48
    맨
    0.46
    고
    0.45
     ज्ञ
    0.45
    akor
    0.44
    ಳ್
    0.44
    ר
    0.44
    št
    0.44
     వే
    0.43
    Act Density 0.000%

    No Known Activations