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

    Neuronpedia

    INDEX
    Explanations

    arrival and check-in plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    कायदा
    0.51
     addirittura
    0.44
     බො
    0.44
     видели
    0.44
     hafta
    0.43
    ლებიც
    0.42
     அடிக்கடி
    0.42
     definitely
    0.41
    ReadAll
    0.41
     తాగ
    0.41
    POSITIVE LOGITS
     afternoon
    0.79
     pomeriggio
    0.77
     Lunch
    0.74
     Optional
    0.71
    Lunch
    0.70
     Afternoon
    0.66
     optional
    0.66
     today
    0.64
     iniziamo
    0.64
     lunch
    0.64
    Act Density 0.018%

    No Known Activations