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

    Neuronpedia

    INDEX
    Explanations

    want to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    E
    0.39
     Zal
    0.39
     Lottery
    0.39
    가의
    0.38
    8
    0.38
     HK
    0.38
    今回の
    0.38
    罗
    0.38
    K
    0.38
    طلح
    0.37
    POSITIVE LOGITS
    UseVisualStyle
    0.44
     advices
    0.41
     chemicals
    0.40
     bumpers
    0.40
    辩
    0.39
     [
    0.39
     yetiş
    0.39
     terzo
    0.38
     ambienti
    0.38
     اړ
    0.38
    Act Density 0.010%

    No Known Activations