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

    Neuronpedia

    INDEX
    Explanations

    Date advertising

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isterschaft
    0.41
     Advancement
    0.36
    arlock
    0.35
    侠
    0.35
    任
    0.35
    ଂ
    0.34
    }$&$
    0.34
     पै
    0.33
     padam
    0.33
     quadrada
    0.33
    POSITIVE LOGITS
     Date
    0.46
     рекла
    0.40
     Bubble
    0.40
    漫畫
    0.39
     DATE
    0.38
    Bubble
    0.38
     advertising
    0.38
    Date
    0.38
     caric
    0.37
     esqu
    0.37
    Act Density 0.001%

    No Known Activations