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

    Neuronpedia

    INDEX
    Explanations

    Jeff Dean

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bearing
    0.41
     Acceleration
    0.40
    Acceleration
    0.39
     Bearing
    0.38
    ட்டு
    0.38
    EndDate
    0.38
     angry
    0.37
    ंडल
    0.36
    mier
    0.36
     bearing
    0.36
    POSITIVE LOGITS
     workmen
    0.42
     зака
    0.39
    죵
    0.38
    িশ
    0.38
     неф
    0.38
     আনুষ্ঠান
    0.37
    igma
    0.37
    玩的
    0.37
     Bragg
    0.37
     vaults
    0.37
    Act Density 0.002%

    No Known Activations