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

    Neuronpedia

    INDEX
    Explanations

    Greek suffixes and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সা
    0.69
     Mum
    0.67
     Ze
    0.61
     लंबाई
    0.61
    既
    0.60
     Specs
    0.59
    é
    0.58
    já
    0.58
    ak
    0.58
    zé
    0.58
    POSITIVE LOGITS
    ρωση
    0.91
    στη
    0.87
    ρηση
    0.85
     furent
    0.82
    leece
    0.78
    нення
    0.77
    λη
    0.74
     arrondies
    0.74
    νη
    0.74
     corretamente
    0.74
    Act Density 0.024%

    No Known Activations