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

    Neuronpedia

    INDEX
    Explanations

    descriptions of states or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ద్య
    0.49
    Izq
    0.48
    Drugs
    0.48
    íj
    0.48
    Businesses
    0.47
     doenças
    0.47
    ExternalTaskPojo
    0.46
    Prz
    0.46
     coûte
    0.46
     каждом
    0.46
    POSITIVE LOGITS
     Plus
    0.46
     transitioning
    0.44
     aforementioned
    0.44
     designated
    0.43
     (
    0.42
     umbrella
    0.42
     Association
    0.41
    0.40
     Tier
    0.40
     liberation
    0.40
    Act Density 0.008%

    No Known Activations