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

    Neuronpedia

    INDEX
    Explanations

    time of day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Virat
    0.50
    ד
    0.48
     Cause
    0.47
    1
    0.47
    These
    0.46
     liczb
    0.45
     কাগজে
    0.45
            
    0.44
    Mein
    0.44
    这是一个
    0.43
    POSITIVE LOGITS
     hora
    0.79
     hours
    0.73
     hour
    0.73
     horas
    0.70
     సమయంలో
    0.70
     час
    0.69
    о
    0.66
    ко
    0.66
    ع
    0.66
     heures
    0.65
    Act Density 0.144%

    No Known Activations