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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wrap
    -0.06
     admits
    -0.06
     Greenwood
    -0.06
    .BorderStyle
    -0.06
    ol
    -0.06
     indx
    -0.06
    (Line
    -0.06
     prisoner
    -0.06
     �
    -0.06
     Colum
    -0.06
    POSITIVE LOGITS
     invokevirtual
    0.07
    ΙΚΟ
    0.07
     printable
    0.06
    IRS
    0.06
    _↵
    0.06
    aurus
    0.06
     implicitly
    0.06
     باز
    0.06
     Airbus
    0.06
    )↵↵
    0.06
    Act Density 0.003%

    No Known Activations