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

    Neuronpedia

    INDEX
    Explanations

    g

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    264
    -0.07
    谈
    -0.06
    нить
    -0.06
     mom
    -0.06
    oux
    -0.06
    35
    -0.06
    combo
    -0.06
    ynn
    -0.05
    inston
    -0.05
    ’int
    -0.05
    POSITIVE LOGITS
    ]';↵
    0.07
     neon
    0.07
    )'],↵
    0.07
    '})↵
    0.07
     Neon
    0.07
     apply
    0.07
    .ErrorMessage
    0.06
    ceae
    0.06
    )],↵
    0.06
     phút
    0.06
    Act Density 0.551%

    No Known Activations