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

    Neuronpedia

    INDEX
    Explanations

    code conditionals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     решений
    1.30
    ية
    1.20
     concatenated
    1.18
    ன்
    1.15
     решения
    1.14
     billionaire
    1.13
    oscale
    1.11
    го
    1.09
     coupling
    1.08
    िल्‍
    1.07
    POSITIVE LOGITS
    এছ
    1.21
    l
    1.11
    ায়
    1.04
    এটা
    1.03
    संपादन
    1.02
     ساتھ
    1.00
     austenite
    0.97
    ια
    0.96
    mouseover
    0.95
     auta
    0.94
    Act Density 0.025%

    No Known Activations