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

    Neuronpedia

    INDEX
    Explanations

    number of attempts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x80>
    0.52
    Fond
    0.40
    <0x96>
    0.39
    verwaltung
    0.39
    。
    0.39
     devastated
    0.39
    kommer
    0.39
     YoY
    0.38
    <0x86>
    0.37
    <0xAC>
    0.37
    POSITIVE LOGITS
     или
    0.65
     وم
    0.63
    ⟋
    0.63
     அல்லது
    0.61
     లేదా
    0.58
    이나
    0.57
     आणि
    0.57
     மற்றும்
    0.57
     अथवा
    0.56
     Pathways
    0.56
    Act Density 0.001%

    No Known Activations