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

    Neuronpedia

    INDEX
    Explanations

    family relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     school
    0.72
     kering
    0.71
    stack
    0.70
    tick
    0.70
     තිබ
    0.69
    agnetic
    0.69
    astics
    0.68
    School
    0.67
     stack
    0.67
     ато
    0.65
    POSITIVE LOGITS
     daughter
    3.13
     daughters
    2.80
     son
    2.74
     sons
    2.67
     offspring
    2.63
     Daughter
    2.58
     figli
    2.54
     hijos
    2.50
    daughter
    2.50
    儿子
    2.49
    Act Density 0.181%

    No Known Activations