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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    研制
    -0.08
     Hess
    -0.08
    ⭞
    -0.07
     poc
    -0.07
    腒
    -0.07
    轩辕
    -0.07
    떽
    -0.07
    ma
    -0.07
    ڬ
    -0.07
    首家
    -0.07
    POSITIVE LOGITS
     Tem
    0.08
    ,to
    0.08
    _partition
    0.07
     soaking
    0.07
    EIF
    0.07
    HORT
    0.07
    ynthesis
    0.07
    ConnectionFactory
    0.07
     negative
    0.07
    _words
    0.07
    Act Density 0.030%

    No Known Activations