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

    Neuronpedia

    INDEX
    Explanations

    event descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tpl
    -0.07
    ►
    -0.07
    权重
    -0.07
     Trap
    -0.06
    _annotation
    -0.06
    (Document
    -0.06
     Joanna
    -0.06
     cx
    -0.06
    现实中
    -0.06
    ductive
    -0.06
    POSITIVE LOGITS
    (Of
    0.07
     послед
    0.07
     그러
    0.06
    ро
    0.06
    _ut
    0.06
     Sne
    0.06
     의
    0.06
     نهائي
    0.06
     continues
    0.06
     �
    0.06
    Act Density 0.142%

    No Known Activations