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

    Neuronpedia

    INDEX
    Explanations

    non- words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Beads
    0.75
     Laundry
    0.68
     Antioxid
    0.68
     Detox
    0.67
     sauf
    0.66
     Headphones
    0.66
     Defines
    0.66
     Catalyst
    0.65
     Blend
    0.64
     Meditation
    0.63
    POSITIVE LOGITS
    -
    1.83
    -,
    1.26
    -)
    1.23
    -/
    1.18
    -$\
    1.14
    -(
    1.13
    -​
    1.10
    -]
    1.09
    -$
    1.08
    -'
    1.06
    Act Density 0.313%

    No Known Activations