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

    Neuronpedia

    INDEX
    Explanations

    classes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Granny
    -0.07
    (=)
    -0.06
    ฟอร
    -0.06
     Yugosl
    -0.06
    \Mapping
    -0.06
     Married
    -0.06
     Grid
    -0.06
     cynical
    -0.06
    mph
    -0.06
    ])/
    -0.06
    POSITIVE LOGITS
     Opportunities
    0.06
    Honda
    0.06
    �
    0.06
     KW
    0.06
    ूच
    0.06
     survey
    0.06
     متن
    0.06
     RM
    0.06
    _CSS
    0.06
     Rockies
    0.06
    Act Density 0.000%

    No Known Activations