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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ourage
    -0.08
    ombie
    -0.07
     RBI
    -0.07
     Wend
    -0.07
     nour
    -0.07
    .Tween
    -0.06
     注
    -0.06
    EH
    -0.06
    725
    -0.06
     Weinstein
    -0.06
    POSITIVE LOGITS
     extras
    0.07
     investigations
    0.07
    acles
    0.06
     investigation
    0.06
    Reports
    0.06
    _REFERER
    0.06
     Conduct
    0.06
    /column
    0.06
     tests
    0.06
     провести
    0.06
    Act Density 0.162%

    No Known Activations