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

    Neuronpedia

    INDEX
    Explanations

    at [ | work | the]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     at
    1.69
    at
    1.32
     atthe
    1.30
     At
    1.28
    At
    1.18
     tại
    1.13
    atthe
    1.01
     ณ
    0.93
     AT
    0.90
     Москвы
    0.90
    POSITIVE LOGITS
    탓
    0.95
     kung
    0.95
    ประมาณ
    0.87
     preconceived
    0.87
    spice
    0.86
     bcrypt
    0.86
    razine
    0.82
     γν
    0.80
    wirtschaft
    0.80
    accessory
    0.80
    Act Density 0.055%

    No Known Activations