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

    Neuronpedia

    INDEX
    Explanations

    long term

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    짧
    1.07
     کوتاه
    1.01
     gọn
    1.00
     $(<
    0.96
    Short
    0.96
    🤏
    0.94
     短
    0.94
     brevi
    0.94
    扼
    0.91
    ature
    0.88
    POSITIVE LOGITS
    parseLong
    1.34
    standing
    1.08
     overdue
    1.07
     ago
    1.06
    uei
    1.03
    itudinal
    1.00
    drawn
    0.99
    haired
    0.96
    awaited
    0.95
     awaited
    0.93
    Act Density 0.075%

    No Known Activations