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

    Neuronpedia

    INDEX
    Explanations

    Remove, Toss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     your
    0.81
     yourself
    0.77
     lütfen
    0.75
    你的
    0.71
     votre
    0.69
    please
    0.66
     iyong
    0.66
    your
    0.66
    你
    0.66
     thine
    0.65
    POSITIVE LOGITS
     Reverse
    0.58
     Whereas
    0.53
     Bahkan
    0.53
    aurait
    0.52
     Historically
    0.51
     M
    0.50
     Even
    0.50
     Даже
    0.50
     আদৌ
    0.50
     Ре
    0.50
    Act Density 0.000%

    No Known Activations