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

    Neuronpedia

    INDEX
    Explanations

    hubris or hugely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Face
    0.41
     Brand
    0.40
     Outfit
    0.39
     face
    0.39
     Wie
    0.39
    IZING
    0.38
     Chim
    0.38
     DMS
    0.38
    izing
    0.37
     SBI
    0.37
    POSITIVE LOGITS
    bub
    0.55
    ariously
    0.47
    achery
    0.46
     debacle
    0.45
    ris
    0.44
    geoning
    0.44
    ंडर
    0.44
    drum
    0.42
    Bub
    0.41
    anigans
    0.41
    Act Density 0.006%

    No Known Activations