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

    Neuronpedia

    INDEX
    Explanations

    distinct items or segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ሁሉ
    0.36
    Certain
    0.34
     తొలి
    0.33
     داخلی
    0.32
     Partially
    0.32
     முழு
    0.31
    こうした
    0.31
    JScripts
    0.30
     суть
    0.30
     ಕೆಲವು
    0.30
    POSITIVE LOGITS
     component
    0.77
     section
    0.67
     portion
    0.61
     Component
    0.54
     komponent
    0.54
    方面的
    0.54
    section
    0.54
     option
    0.53
    component
    0.53
     module
    0.51
    Act Density 0.109%

    No Known Activations