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

    Neuronpedia

    INDEX
    Explanations

    theatre and drama

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alumni
    0.38
     फोटोशूट
    0.38
    locking
    0.38
    Mutex
    0.38
    மாண
    0.38
    蒨
    0.37
     ফ্র
    0.36
    KeyState
    0.36
    ObjectTemp
    0.36
     красиво
    0.36
    POSITIVE LOGITS
     masks
    0.58
    masks
    0.58
     mask
    0.55
    Mask
    0.55
     Masks
    0.50
    mask
    0.50
     máscara
    0.48
     Mask
    0.48
     masked
    0.46
     spectacles
    0.46
    Act Density 0.015%

    No Known Activations