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

    Neuronpedia

    INDEX
    Explanations

    days of the week and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     top
    0.59
    top
    0.53
     extern
    0.52
     compres
    0.52
     start
    0.51
     target
    0.51
     arising
    0.49
    닳
    0.49
     mind
    0.49
    blank
    0.48
    POSITIVE LOGITS
     Jumat
    0.61
    eşit
    0.60
     samedi
    0.60
     Sabtu
    0.58
     ఆది
    0.57
    Saturday
    0.57
    avond
    0.56
     domenica
    0.56
    াদুর
    0.55
     dimanche
    0.55
    Act Density 0.030%

    No Known Activations