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

    Neuronpedia

    INDEX
    Explanations

    spur, spurt, restaurants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bb
    0.42
     merge
    0.39
     Recht
    0.38
     text
    0.38
     Text
    0.38
     merged
    0.38
     Ladd
    0.36
     recto
    0.36
     ende
    0.35
     tav
    0.35
    POSITIVE LOGITS
    齦
    0.38
    lectric
    0.36
     {}\
    0.36
    业绩
    0.36
    හැ
    0.35
    :],
    0.34
     информационной
    0.34
     प्रोडक्शन
    0.34
     విధాన
    0.34
    0.34
    Act Density 0.005%

    No Known Activations