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

    Neuronpedia

    INDEX
    Explanations

    License asterisk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ));
↵
↵
    -0.07
     fronts
    -0.07
    .bi
    -0.06
    ]);
↵
↵
    -0.06
    ीत
    -0.06
    /K
    -0.06
    Bi
    -0.06
    ):
↵
↵
    -0.06
    ]):
↵
    -0.06
     ".";↵
    -0.06
    POSITIVE LOGITS
    今天
    0.07
    _SOURCE
    0.06
    _lin
    0.06
     failing
    0.06
    (pm
    0.06
    ерше
    0.06
    λιά
    0.06
    (Array
    0.06
    -pt
    0.06
    weekly
    0.06
    Act Density 0.012%

    No Known Activations