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

    Neuronpedia

    INDEX
    Explanations

    conjunctions adding information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    0.43
     አይነት
    0.40
    2
    0.38
     outdoor
    0.37
     brains
    0.37
    othy
    0.36
    themed
    0.36
    or
    0.35
    Cs
    0.35
     cook
    0.35
    POSITIVE LOGITS
     inoltre
    0.62
     furthermore
    0.53
     또한
    0.46
     ৃ
    0.44
     daarbij
    0.43
     അതിന്റെ
    0.42
    yrıca
    0.42
    呻
    0.41
    또한
    0.41
     moreover
    0.40
    Act Density 0.025%

    No Known Activations