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

    Neuronpedia

    INDEX
    Explanations

    blues and greens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    白天
    0.49
    databind
    0.45
    etty
    0.44
    project
    0.44
    ennen
    0.44
    ib
    0.44
    antz
    0.44
    undance
    0.43
    alev
    0.43
    il
    0.43
    POSITIVE LOGITS
    л
    0.80
     in
    0.66
    ב
    0.65
     offshore
    0.60
    ও
    0.51
    ق
    0.51
    ক
    0.50
     offshoring
    0.50
     rims
    0.50
     Inquisition
    0.49
    Act Density 0.002%

    No Known Activations