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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hacked
    -0.07
    رسی
    -0.06
     dividing
    -0.06
     surveyed
    -0.06
    ;,
    -0.06
    MA
    -0.06
     S
    -0.06
     ap
    -0.06
     indicted
    -0.06
     Пар
    -0.06
    POSITIVE LOGITS
    !')↵
    0.07
    'LBL
    0.07
    )";
↵
    0.07
    bench
    0.06
    ]\
    0.06
    ']]
    0.06
     örgüt
    0.06
    .auth
    0.06
    iq
    0.06
    '])){↵
    0.06
    Act Density 0.005%

    No Known Activations