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

    Neuronpedia

    INDEX
    Explanations

    Scientific research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    降水
    -0.07
    except
    -0.07
     giữ
    -0.07
    arnings
    -0.07
     except
    -0.07
    /reference
    -0.06
    Thin
    -0.06
    ););↵
    -0.06
     Bean
    -0.06
    @Test
    -0.06
    POSITIVE LOGITS
     Mit
    0.07
     Mata
    0.07
     Saúde
    0.07
    .Path
    0.07
    .stream
    0.07
    Ｕ
    0.07
    ."'
    0.07
     emlrt
    0.06
     לעבור
    0.06
     имени
    0.06
    Act Density 0.145%

    No Known Activations