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

    Neuronpedia

    INDEX
    Explanations

    Foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itſelf
    -1.32
     myſelf
    -1.27
     mijne
    -1.23
     Monfieur
    -1.22
     figliu
    -1.15
     houſe
    -1.14
     þat
    -1.13
     literaria
    -1.13
     themſelves
    -1.12
     Efq
    -1.12
    POSITIVE LOGITS
     tr
    0.73
     tra
    0.69
     mag
    0.69
     ar
    0.66
     ped
    0.66
     che
    0.65
     ma
    0.63
     tem
    0.63
     ro
    0.63
     der
    0.63
    Act Density 0.181%

    No Known Activations