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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    Numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    drücken
    -0.52
     Архиви
    -0.49
     دهنده
    -0.46
    drück
    -0.45
    ย์
    -0.44
    ų
    -0.43
    ]]);
    -0.42
    ()]
    -0.42
    こそ
    -0.42
     Merritt
    -0.42
    POSITIVE LOGITS
    DockStyle
    1.05
    rungsseite
    0.88
    ########.
    0.88
    abestanden
    0.84
    RegressionTest
    0.78
    SBATCH
    0.75
    Rhestr
    0.73
     kasarigan
    0.72
    تقاوى
    0.69
    脚注の使い方
    0.69
    Act Density 11.467%

    No Known Activations