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

    Neuronpedia

    INDEX
    Explanations

    research studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OGND
    -0.92
     OFDb
    -0.67
     ***!
    -0.67
    elemField
    -0.63
    colgroup
    -0.62
     kasarigan
    -0.61
    Билгалдахарш
    -0.60
    Jeografia
    -0.59
    transQ
    -0.58
    Referencie
    -0.58
    POSITIVE LOGITS
     Diſ
    0.58
     Conſ
    0.58
    ± 
    0.56
     Houſe
    0.54
     context
    0.54
     contex
    0.54
    ανε
    0.52
     Efq
    0.52
    context
    0.51
    ządz
    0.51
    Act Density 0.010%

    No Known Activations