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

    Neuronpedia

    INDEX
    Explanations

    at the or always

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cuyos
    1.07
    िप्ट
    1.02
    蘄
    0.98
     mayhem
    0.97
     disturbances
    0.96
     réessayer
    0.94
     සහ
    0.94
    avgsalary
    0.93
     disturbing
    0.92
     ሁሉም
    0.91
    POSITIVE LOGITS
    nya
    0.85
    oku
    0.83
     Kanban
    0.77
    orel
    0.74
    t
    0.73
    naver
    0.73
     benda
    0.72
    ostat
    0.71
    att
    0.71
    と言う
    0.70
    Act Density 0.000%

    No Known Activations