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

    Neuronpedia

    INDEX
    Explanations

    The Basics, Security, Personal Stories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     इच्छ
    0.78
     वगैर
    0.77
     seniority
    0.75
     surcharge
    0.73
    셔
    0.72
     пото
    0.71
     کردہ
    0.70
    quant
    0.70
    да
    0.70
     statistique
    0.70
    POSITIVE LOGITS
    아
    1.00
    Ah
    0.88
    率先
    0.87
    ственная
    0.86
    apak
    0.85
    rah
    0.84
    ственной
    0.82
     특징
    0.82
    ह्म
    0.82
     توضیح
    0.81
    Act Density 0.000%

    No Known Activations