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

    Neuronpedia

    INDEX
    Explanations

    code and databases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eten
    -0.07
    暂缓
    -0.07
    盼望
    -0.07
    笳
    -0.06
     및
    -0.06
     following
    -0.06
    plan
    -0.06
    ﮔ
    -0.06
    有条件的
    -0.06
    etes
    -0.06
    POSITIVE LOGITS
     muchos
    0.07
     mentor
    0.07
     Mig
    0.07
     السوري
    0.06
     bri
    0.06
     sửa
    0.06
    ｻ
    0.06
    matching
    0.06
     ✓
    0.06
    _bounds
    0.06
    Act Density 0.180%

    No Known Activations