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

    Neuronpedia

    INDEX
    Explanations

    thanks and courtesy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    겠다는
    0.40
     zroz
    0.40
     했을
    0.39
    睏
    0.37
    гиз
    0.36
    ब्दिक
    0.36
     decompositions
    0.36
    RealPath
    0.36
    立つ
    0.35
    bnf
    0.34
    POSITIVE LOGITS
     courtesy
    3.06
     Courtesy
    2.64
    Courtesy
    2.48
    cour
    2.28
     cour
    1.66
     thanks
    1.60
     cortes
    1.58
     compliments
    1.57
     COUR
    1.55
    thanks
    1.54
    Act Density 0.013%

    No Known Activations