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

    Neuronpedia

    INDEX
    Explanations

    Non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /Object
    -0.07
    eness
    -0.07
    发力
    -0.07
    Skipping
    -0.06
    .ak
    -0.06
    .Alignment
    -0.06
    /random
    -0.06
    SharedPointer
    -0.06
     potent
    -0.06
    万股
    -0.06
    POSITIVE LOGITS
    iais
    0.07
    聽到
    0.07
    жа
    0.07
    خد
    0.07
    积
    0.07
    lu
    0.07
    >Returns
    0.07
    翦
    0.07
    笈
    0.06
    حس
    0.06
    Act Density 0.147%

    No Known Activations