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

    Neuronpedia

    INDEX
    Explanations

    Related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     newer
    -0.06
     není
    -0.06
     Bryant
    -0.06
     BUF
    -0.06
     /^\
    -0.06
    Advertisement
    -0.06
    .Raw
    -0.06
     nrows
    -0.06
    /raw
    -0.06
    ailure
    -0.06
    POSITIVE LOGITS
     implementing
    0.07
     […
    0.07
     glor
    0.07
     示例
    0.06
     lãi
    0.06
     susceptible
    0.06
     gli
    0.06
            
    0.06
     проблем
    0.06
     піс
    0.06
    Act Density 0.003%

    No Known Activations