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

    Neuronpedia

    INDEX
    Explanations

    cause and effect

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    idos
    -0.07
     conservatism
    -0.07
     passer
    -0.07
    uzzi
    -0.06
     ero
    -0.06
    idores
    -0.06
     generalized
    -0.06
    еного
    -0.06
    atör
    -0.06
    ầng
    -0.06
    POSITIVE LOGITS
    .getSelection
    0.07
     зали
    0.07
    gene
    0.06
    /facebook
    0.06
    .AnchorStyles
    0.06
    arth
    0.06
     صفحه
    0.06
     submarines
    0.06
     склад
    0.06
    。あ
    0.06
    Act Density 0.107%

    No Known Activations