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

    Neuronpedia

    INDEX
    Explanations

    sets the stage for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্লাস
    0.36
     afforded
    0.36
     সাপ্তাহিক
    0.35
     aspects
    0.35
    ərb
    0.35
     Aspects
    0.35
     spanned
    0.34
     drills
    0.34
     withstand
    0.33
     प्रिय
    0.33
    POSITIVE LOGITS
     stage
    1.13
     groundwork
    1.05
    舞台
    0.91
    stage
    0.86
     foundation
    0.83
     Stage
    0.80
    Stage
    0.80
     tone
    0.79
    STAGE
    0.77
     precedent
    0.73
    Act Density 0.024%

    No Known Activations