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

    Neuronpedia

    INDEX
    Explanations

    your physical, the slabs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     REQUIRE
    0.49
     தேவை
    0.47
    🥹
    0.47
     nuanced
    0.46
    YNAMIC
    0.46
     ALWAYS
    0.45
    ALWAYS
    0.45
     ideally
    0.44
     सदैव
    0.44
     profoundly
    0.43
    POSITIVE LOGITS
    <{},
    0.43
    ینک
    0.43
     touted
    0.43
     Consumer
    0.41
    驼
    0.40
    设备的
    0.39
    0.39
    ্ষিকী
    0.38
    ൊ
    0.38
    κή
    0.38
    Act Density 0.160%

    No Known Activations