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

    Neuronpedia

    INDEX
    Explanations

    toys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    เซ
    -0.07
    ancement
    -0.06
    petto
    -0.06
     PROFITS
    -0.06
    lda
    -0.06
    datagrid
    -0.06
    AccountId
    -0.06
     dáv
    -0.06
    .fore
    -0.06
     Ae
    -0.05
    POSITIVE LOGITS
    _decl
    0.08
    istr
    0.07
    (([
    0.06
     GLint
    0.06
    一切
    0.06
     Puppy
    0.06
     Routing
    0.06
     tensorflow
    0.06
    igion
    0.06
    ]));
↵
    0.06
    Act Density 0.008%

    No Known Activations