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

    Neuronpedia

    INDEX
    Explanations

    states that or prevents me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अपनी
    0.51
    اپنی
    0.48
     and
    0.45
     according
    0.44
    अपने
    0.44
     अपने
    0.43
     தமது
    0.43
    ally
    0.43
     اپنی
    0.42
     swoich
    0.42
    POSITIVE LOGITS
    ਾਨੂੰ
    0.52
    ：“
    0.49
    ："
    0.47
     нам
    0.45
     rằng
    0.45
    ว่า
    0.44
    ശു
    0.44
    ：「
    0.44
    suggest
    0.43
     sugger
    0.43
    Act Density 0.006%

    No Known Activations