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

    Neuronpedia

    INDEX
    Explanations

    lambda in code definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Խ
    0.97
    हत्या
    0.95
    sj
    0.91
     کتاب
    0.89
    sung
    0.85
     نوا
    0.85
    sellers
    0.85
     этому
    0.84
     กล่าว
    0.84
    槎
    0.84
    POSITIVE LOGITS
    اری
    0.92
    ри
    0.90
    5
    0.84
    ể
    0.82
    <0x80>
    0.81
     musculaire
    0.81
    ್ಯೂ
    0.81
    4
    0.80
    F
    0.80
    1
    0.79
    Act Density 0.001%

    No Known Activations