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

    Neuronpedia

    INDEX
    Explanations

    coffee grinding and consistency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    8
    0.68
    не
    0.66
    7
    0.64
    9
    0.58
    ٧
    0.57
    ِي
    0.55
    je
    0.55
    ii
    0.55
    ៩
    0.55
    Construction
    0.54
    POSITIVE LOGITS
     grind
    0.73
     grinding
    0.68
     Rift
    0.66
     دوسرا
    0.64
     تباہ
    0.62
     deafness
    0.62
     وقتی
    0.61
     myopia
    0.59
     Grind
    0.58
    cosity
    0.58
    Act Density 0.007%

    No Known Activations