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

    Neuronpedia

    INDEX
    Explanations

    power, boost, signaling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Arithmetic
    0.42
    Indices
    0.40
    Refreshing
    0.39
     strewn
    0.39
    Including
    0.39
    USION
    0.39
     ANOTHER
    0.38
     termasuk
    0.38
     inescap
    0.38
    жений
    0.37
    POSITIVE LOGITS
     watts
    0.42
     vitae
    0.42
     يا
    0.42
     paragraph
    0.41
     wattage
    0.40
     propelling
    0.40
    䚯
    0.40
     chairman
    0.40
     Boost
    0.39
     boosting
    0.39
    Act Density 0.000%

    No Known Activations