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

    Neuronpedia

    INDEX
    Explanations

    will miss you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     behandeling
    0.71
     doll
    0.70
    印
    0.68
    인
    0.67
     преде
    0.66
    ধ
    0.66
     Schul
    0.65
     সিরাপ
    0.65
    adham
    0.65
    承诺
    0.65
    POSITIVE LOGITS
     miss
    1.70
     missed
    1.51
     missing
    1.51
     misses
    1.49
     Missing
    1.48
    miss
    1.40
    Missing
    1.38
     MISS
    1.36
    missing
    1.35
     Miss
    1.33
    Act Density 0.054%

    No Known Activations