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

    Neuronpedia

    INDEX
    Explanations

    initial screening job filter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     January
    0.42
     disgust
    0.42
    ور
    0.41
     Vil
    0.40
     Americana
    0.40
     soci
    0.40
     uniforms
    0.39
     gems
    0.39
     oper
    0.38
    ྕ
    0.38
    POSITIVE LOGITS
    ovascular
    0.41
    impl
    0.40
    ewall
    0.39
     ساين
    0.38
    紆
    0.37
    util
    0.37
    來
    0.37
    鬥
    0.36
    ificial
    0.36
    蚪
    0.36
    Act Density 0.002%

    No Known Activations