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

    Neuronpedia

    INDEX
    Explanations

    Percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Weber
    -0.07
    hos
    -0.07
     grapes
    -0.07
     Those
    -0.07
     dle
    -0.07
     блю
    -0.07
     Smith
    -0.06
     QDir
    -0.06
     deported
    -0.06
     VW
    -0.06
    POSITIVE LOGITS
     ก
    0.08
    -stream
    0.07
    닝
    0.06
    ps
    0.06
     �
    0.06
     Newsletter
    0.06
     StringWriter
    0.06
     tyranny
    0.06
    erview
    0.06
     additional
    0.06
    Act Density 0.023%

    No Known Activations