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

    Neuronpedia

    INDEX
    Explanations

    below descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oven
    0.44
     informer
    0.43
     graphs
    0.43
     array
    0.42
     ponds
    0.41
     ingestion
    0.41
     pendants
    0.41
     implicate
    0.40
     websites
    0.40
     arrays
    0.40
    POSITIVE LOGITS
    Ī
    0.56
    Ĭ
    0.49
    Į
    0.46
    ī
    0.45
     Pickup
    0.40
     লাহ
    0.40
     Special
    0.38
    Supply
    0.38
    ĭ
    0.38
     BMW
    0.38
    Act Density 0.050%

    No Known Activations