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

    Neuronpedia

    INDEX
    Explanations

    fundamentally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     K
    0.57
     J
    0.49
     McCl
    0.46
     Sylvia
    0.45
     THAT
    0.45
    y
    0.45
     G
    0.44
     George
    0.43
     MRS
    0.43
     Q
    0.42
    POSITIVE LOGITS
     применение
    0.53
    legung
    0.52
    差異
    0.52
    爭
    0.51
     процентов
    0.50
     equipamento
    0.50
    Difference
    0.49
     cálculo
    0.49
     redução
    0.49
     función
    0.48
    Act Density 0.011%

    No Known Activations