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

    Neuronpedia

    INDEX
    Explanations

    control and order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Syndrome
    0.24
    np
    0.23
     HCI
    0.22
     NPD
    0.22
     HC
    0.21
     appunto
    0.21
     degli
    0.21
     Surprise
    0.21
     NPS
    0.21
     চৈতন্য
    0.21
    POSITIVE LOGITS
    ให้กับ
    0.29
    하면서
    0.24
     svojim
    0.24
     asupra
    0.23
    于
    0.23
    ój
    0.23
     нашим
    0.22
    ঞ্জ
    0.22
    ancourt
    0.21
    resso
    0.21
    Act Density 0.048%

    No Known Activations