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

    Neuronpedia

    INDEX
    Explanations

    words following 'the'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Với
    0.34
    Université
    0.33
     fhould
    0.33
    Bankr
    0.31
     curricula
    0.31
     целях
    0.31
    兽
    0.30
     және
    0.30
    环境中
    0.30
     andRow
    0.30
    POSITIVE LOGITS
    et
    0.29
    t
    0.28
     todo
    0.28
      
    0.28
     Pix
    0.27
     भले
    0.27
     Rak
    0.27
    res
    0.27
     point
    0.26
    riya
    0.26
    Act Density 0.011%

    No Known Activations