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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    there
    -0.07
    %H
    -0.07
     Uncategorized
    -0.06
     ambush
    -0.06
    общ
    -0.06
    <File
    -0.06
    Kir
    -0.06
     eater
    -0.06
     domest
    -0.06
    .vol
    -0.06
    POSITIVE LOGITS
     Supplementary
    0.06
    (pow
    0.06
    ]?
    0.06
    <?=
    0.06
     progression
    0.06
    ９
    0.06
    ..↵↵
    0.06
     tot
    0.06
     Joint
    0.06
     może
    0.06
    Act Density 0.050%

    No Known Activations