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

    Neuronpedia

    INDEX
    Explanations

    title

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Grave
    -0.07
    тель
    -0.06
     Điều
    -0.06
    ratio
    -0.06
     maternal
    -0.06
     граж
    -0.06
    是一项
    -0.06
     investigation
    -0.06
     appendix
    -0.06
    ição
    -0.06
    POSITIVE LOGITS
    .resources
    0.07
    NCY
    0.07
     dictionaryWith
    0.07
    hesive
    0.06
    BBC
    0.06
    raphics
    0.06
    Snap
    0.06
     Quotes
    0.06
    аются
    0.06
    ceries
    0.06
    Act Density 0.000%

    No Known Activations