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

    Neuronpedia

    INDEX
    Explanations

    made

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    
    -0.80
    HasAnnotation
    -0.58
     Ret
    -0.54
    saraba
    -0.53
    avadoc
    -0.53
    nodoc
    -0.52
     通販
    -0.52
     CascadeType
    -0.52
     expedi
    -0.51
    numerusform
    -0.51
    POSITIVE LOGITS
     up
    0.73
     originais
    0.72
     engraçadas
    0.69
     creazione
    0.65
     célèbres
    0.64
     mêmes
    0.61
     when
    0.60
    лючение
    0.59
     caseros
    0.56
    BoxLayout
    0.55
    Act Density 0.002%

    No Known Activations