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

    Neuronpedia

    INDEX
    Explanations

    code response statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     furnishes
    0.48
    cklenburg
    0.42
    公布
    0.39
    めます
    0.39
    Crit
    0.38
     equates
    0.38
     ലോ
    0.38
    кура
    0.38
    ̘
    0.38
    សុ
    0.37
    POSITIVE LOGITS
     promen
    0.40
     पदों
    0.39
     admin
    0.38
    ທີ່
    0.38
     intermedi
    0.38
    ä
    0.37
    divider
    0.37
    adder
    0.36
     limiti
    0.36
    抓住
    0.36
    Act Density 0.000%

    No Known Activations