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

    Neuronpedia

    INDEX
    Explanations

    miles per

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tak
    0.88
    Се
    0.87
    1
    0.86
    8
    0.85
    Ш
    0.82
    4
    0.82
    На
    0.80
    Си
    0.80
     ли
    0.80
    3
    0.79
    POSITIVE LOGITS
     gerar
    0.83
     transformar
    0.81
     estructural
    0.78
     직선
    0.78
     transformação
    0.78
     rumbo
    0.77
     “‘
    0.77
     northward
    0.77
     demolished
    0.76
    ের
    0.76
    Act Density 0.000%

    No Known Activations