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

    Neuronpedia

    INDEX
    Explanations

    events and vocabulary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kerchief
    0.41
     display
    0.39
    😐
    0.37
    atoes
    0.37
     ഉത്സ
    0.37
    <unused58>
    0.36
     ειδ
    0.36
     líneas
    0.36
     voies
    0.36
     dailySales
    0.36
    POSITIVE LOGITS
    Influ
    0.39
    文
    0.38
    解決
    0.38
    емом
    0.38
    漂
    0.38
    風格
    0.37
    hosted
    0.37
    cex
    0.36
    ólogo
    0.36
    かず
    0.36
    Act Density 0.000%

    No Known Activations