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

    Neuronpedia

    INDEX
    Explanations

    reporting suspicious activity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🆘
    -0.07
    依旧是
    -0.06
    엗
    -0.06
    칕
    -0.06
    윌
    -0.06
    (contact
    -0.06
    土耳其
    -0.06
     août
    -0.06
    ঈ
    -0.06
    ﲏ
    -0.06
    POSITIVE LOGITS
    )";
↵
    0.07
    租
    0.07
     convince
    0.07
     bump
    0.07
    青春
    0.07
    .tokens
    0.07
    .appendTo
    0.07
    短期
    0.07
    arsed
    0.07
     surgeon
    0.07
    Act Density 0.035%

    No Known Activations