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

    Neuronpedia

    INDEX
    Explanations

    HBO shows and streaming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    j
    1.60
    y
    1.53
    r
    1.44
    k
    1.40
    v
    1.34
    re
    1.28
    w
    1.25
    yj
    1.24
    iat
    1.22
    לים
    1.20
    POSITIVE LOGITS
    ان
    1.30
     cohom
    1.11
    蔷
    1.07
    Tooltip
    1.05
    الج
    1.04
     بیشتر
    1.02
     واست
    1.02
    nál
    0.97
     لیے
    0.96
    Costs
    0.96
    Act Density 0.001%

    No Known Activations