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

    Neuronpedia

    INDEX
    Explanations

    commas followed by common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     they
    1.12
     whose
    1.09
     caused
    1.07
     thats
    1.06
     containing
    1.03
     its
    1.03
     which
    1.02
     causing
    1.01
     where
    0.96
     involving
    0.95
    POSITIVE LOGITS
    Perfil
    0.99
    /,
    0.97
    :,
    0.94
    ..,
    0.91
    Productos
    0.90
    Mathemat
    0.88
    Constraints
    0.88
    Projeto
    0.87
     :,
    0.87
    ,",
    0.85
    Act Density 0.224%

    No Known Activations