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

    Neuronpedia

    INDEX
    Explanations

    mentions of numbers or quantities

    oai_token-act-pair · gemini-2.0-flash

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.85
    +#+#
    -0.60
    TestBed
    -0.57
     charité
    -0.57
    ghest
    -0.56
     laterale
    -0.55
    chafft
    -0.54
    amsmath
    -0.54
     tắt
    -0.54
    UnusedPrivate
    -0.54
    POSITIVE LOGITS
     незавершена
    0.74
    Jegyzetek
    0.52
    хьтан
    0.49
    Easy
    0.47
    AsUp
    0.46
    ьаж
    0.46
    InjectAttribute
    0.46
    closedir
    0.45
    Oise
    0.45
    SBATCH
    0.44
    Act Density 6.033%

    No Known Activations