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

    Neuronpedia

    INDEX
    Explanations

    Foreign language beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BOTH
    1.13
    menus
    1.10
     traverses
    1.10
    翮
    1.08
    osynthesis
    1.06
    getString
    1.06
     excepted
    1.05
    codile
    1.05
     ঘটেছে
    1.05
    CENTER
    1.05
    POSITIVE LOGITS
     expl
    1.09
     desto
    1.09
    शुभ
    1.05
    äng
    1.05
     ベ
    1.04
     메
    0.99
     gdje
    0.99
    마
    0.99
     donde
    0.99
     yür
    0.97
    Act Density 0.000%

    No Known Activations