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

    Neuronpedia

    INDEX
    Explanations

    members/users

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     años
    -0.08
     Trabalho
    -0.08
     Granada
    -0.08
     Justice
    -0.07
     QE
    -0.07
     í
    -0.07
     arguably
    -0.07
     personal
    -0.07
     oficina
    -0.07
     prima
    -0.07
    POSITIVE LOGITS
     którzy
    0.10
     যারা
    0.09
     bitch
    0.09
     kteří
    0.08
     الذين
    0.08
     chaleure
    0.08
    Who
    0.08
     hymn
    0.08
    下載
    0.08
     congratulations
    0.08
    Act Density 0.014%

    No Known Activations