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

    Neuronpedia

    INDEX
    Explanations

    analyze or observe states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     innovación
    0.46
    迷惑
    0.43
    是不是
    0.43
     personnes
    0.42
     identidade
    0.42
     operativos
    0.42
    像
    0.41
     które
    0.41
    ások
    0.41
    民宿
    0.41
    POSITIVE LOGITS
    eb
    0.44
     значительно
    0.43
     சுமார்
    0.42
     Analyze
    0.42
     стр
    0.41
    лия
    0.40
     сот
    0.39
     అత్య
    0.39
    ере
    0.39
     рр
    0.39
    Act Density 0.008%

    No Known Activations