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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PARSER
    -0.08
     congressman
    -0.07
    不见
    -0.07
     deport
    -0.07
    Fuse
    -0.06
    dims
    -0.06
     אלו
    -0.06
    务
    -0.06
    �
    -0.06
     Vie
    -0.06
    POSITIVE LOGITS
    עבד
    0.07
    assandra
    0.07
    ="";↵
    0.07
    "};↵
    0.07
    抽
    0.07
     Password
    0.07
    .blob
    0.06
    𫄨
    0.06
    Elect
    0.06
     lodash
    0.06
    Act Density 0.003%

    No Known Activations