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

    Neuronpedia

    INDEX
    Explanations

    multiple jobs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    duction
    -0.07
    arse
    -0.07
     Giám
    -0.07
    061
    -0.06
    aved
    -0.06
    ews
    -0.06
    Coal
    -0.06
    airobi
    -0.06
    .ค
    -0.06
    ीआई
    -0.06
    POSITIVE LOGITS
    _THEME
    0.07
    =models
    0.07
     Amateur
    0.07
     Monument
    0.06
    _subject
    0.06
     unwanted
    0.06
    .Board
    0.06
    utures
    0.06
    _LIBRARY
    0.06
     Residence
    0.06
    Act Density 0.078%

    No Known Activations