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

    Neuronpedia

    INDEX
    Explanations

    dates and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Especially
    0.39
    尤其
    0.39
     especially
    0.39
    特に
    0.38
     ESPE
    0.37
     Especially
    0.37
     особливо
    0.36
     особенно
    0.36
    특히
    0.34
     Особенно
    0.34
    POSITIVE LOGITS
     shortly
    0.51
     after
    0.46
     بعد
    0.41
     efter
    0.41
     setelah
    0.41
     לאחר
    0.40
    Shortly
    0.40
    after
    0.38
     після
    0.38
     после
    0.37
    Act Density 0.016%

    No Known Activations