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

    Neuronpedia

    INDEX
    Explanations

    Cards Against Humanity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Son
    0.39
    পোষ
    0.39
    خط
    0.38
    forgot
    0.38
    氧化
    0.37
    摇头
    0.36
    accessory
    0.36
    进入
    0.35
    ตอบ
    0.35
     मेवाड़
    0.35
    POSITIVE LOGITS
     campaigns
    0.39
    zq
    0.37
     sens
    0.35
     viser
    0.35
    parseLong
    0.35
     scrutiny
    0.34
     lijkt
    0.34
    Lang
    0.34
     ст
    0.34
     innebär
    0.33
    Act Density 0.000%

    No Known Activations