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

    Neuronpedia

    INDEX
    Explanations

    everyday life

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     don
    0.60
     an
    0.53
     a
    0.52
     eing
    0.52
     on
    0.50
     enteros
    0.50
     deforestation
    0.49
     datos
    0.49
     clear
    0.49
     didn
    0.49
    POSITIVE LOGITS
     повседнев
    0.86
    ordinary
    0.75
    日常
    0.73
     обы
    0.71
     cotidiana
    0.70
    生活中
    0.69
    Ordinary
    0.68
     mundane
    0.68
     ordinary
    0.67
    일상
    0.67
    Act Density 0.020%

    No Known Activations