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

    Neuronpedia

    INDEX
    Explanations

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    К
    1.49
    ز
    1.30
    ו
    1.23
    Т
    1.16
    K
    1.14
    ES
    1.12
    AC
    1.12
    ל
    1.12
    EN
    1.11
    IM
    1.11
    POSITIVE LOGITS
    คุณ
    1.00
     amortization
    0.98
    </h3>
    0.95
    ido
    0.89
     ovation
    0.87
    вого
    0.86
     ajo
    0.85
    一个人
    0.84
     excepcional
    0.82
    ılan
    0.80
    Act Density 0.010%

    No Known Activations