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

    Neuronpedia

    INDEX
    Explanations

    mathematics and geometry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    是否会
    -0.07
    GN
    -0.07
    _Sh
    -0.07
    桴
    -0.07
     careg
    -0.07
    を持
    -0.07
    _PCI
    -0.07
    有这样的
    -0.07
    𝐋
    -0.06
     uLocal
    -0.06
    POSITIVE LOGITS
     proposed
    0.07
    	ff
    0.07
    流程
    0.07
    published
    0.07
    !↵↵
    0.07
    google
    0.07
    лот
    0.07
    (iterator
    0.07
     )
↵
    0.07
    物料
    0.07
    Act Density 0.008%

    No Known Activations