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

    Neuronpedia

    INDEX
    Explanations

    HTML code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     finder
    -0.06
    _instance
    -0.06
    verbatim
    -0.06
     indicator
    -0.06
     closed
    -0.06
    ersistence
    -0.06
     interpreted
    -0.06
    {Name
    -0.06
     Metadata
    -0.05
    ﾐ
    -0.05
    POSITIVE LOGITS
     flawed
    0.08
    -cookie
    0.07
     بور
    0.07
    PRE
    0.07
    藍
    0.07
     rok
    0.07
     Crom
    0.07
     ông
    0.06
    て
    0.06
     대표
    0.06
    Act Density 0.041%

    No Known Activations