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

    Neuronpedia

    INDEX
    Explanations

    math computations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     matching
    -0.08
    LABEL
    -0.08
    פורט
    -0.08
     soar
    -0.08
    乡村
    -0.08
     phố
    -0.07
     Tuesday
    -0.07
     Philadelphia
    -0.07
     drunk
    -0.07
     originating
    -0.07
    POSITIVE LOGITS
    怩
    0.07
    ]<<
    0.07
    똬
    0.06
    必不可
    0.06
    ('*
    0.06
    小吃
    0.06
    젭
    0.06
    Ӟ
    0.06
    螈
    0.06
    ㈼
    0.06
    Act Density 0.094%

    No Known Activations