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

    Neuronpedia

    INDEX
    Explanations

    specific contexts and inputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spotlights
    0.39
     تقری
    0.36
     Progression
    0.36
     प्रतिभाग
    0.36
     selectable
    0.34
     versions
    0.34
     Hesse
    0.34
    Starts
    0.34
    ppable
    0.34
     Rub
    0.34
    POSITIVE LOGITS
    काय
    0.44
     crear
    0.40
     bastard
    0.39
    購買
    0.39
     BadRequest
    0.38
    iquent
    0.38
    ша
    0.38
    計劃
    0.38
    küm
    0.38
    最高の
    0.38
    Act Density 0.001%

    No Known Activations