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

    Neuronpedia

    INDEX
    Explanations

    3D related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    r
    0.78
    )
    0.75
    hips
    0.71
    0.68
    s
    0.68
    (
    0.66
    >
    0.65
    ):
    0.64
    :
    0.63
    =
    0.63
    POSITIVE LOGITS
    ری
    0.81
    на
    0.75
     Haziran
    0.75
     novoProduto
    0.72
     esempio
    0.70
     Produto
    0.70
     botão
    0.68
    ı
    0.68
    ある
    0.67
    ३
    0.66
    Act Density 0.092%

    No Known Activations