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

    Neuronpedia

    INDEX
    Explanations

    if you or it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     그럼
    0.33
     دې
    0.33
     বললাম
    0.33
    尽可能
    0.29
     نرم
    0.29
     م
    0.28
     ไ
    0.28
    mselves
    0.28
     ପ୍ର
    0.28
     เพ
    0.28
    POSITIVE LOGITS
     there
    0.73
     it
    0.66
     they
    0.57
    bbene
    0.54
     theres
    0.48
     you
    0.48
    there
    0.47
     not
    0.46
     thats
    0.46
     هناك
    0.46
    Act Density 0.067%

    No Known Activations