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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Imaging
    -0.08
    焉
    -0.07
    固定
    -0.07
     下
    -0.07
    firm
    -0.07
     nam
    -0.07
    初始化
    -0.06
    -api
    -0.06
    "--
    -0.06
    읶
    -0.06
    POSITIVE LOGITS
    PHP
    0.07
    _DECLS
    0.07
    最大程度
    0.07
     AssemblyCopyright
    0.07
    REFERENCES
    0.07
    吞
    0.06
    duce
    0.06
    rellas
    0.06
    trie
    0.06
     �
    0.06
    Act Density 0.010%

    No Known Activations