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

    Neuronpedia

    INDEX
    Explanations

    Know

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     king
    -1.06
     King
    -1.05
     rights
    -0.95
    King
    -0.90
     Rights
    -0.86
     KING
    -0.85
    InSection
    -0.81
    expandindo
    -0.81
     numberWith
    -0.81
     protoimpl
    -0.80
    POSITIVE LOGITS
     for
    0.45
     dimentic
    0.44
    arak
    0.41
    お
    0.39
    l
    0.39
     aimé
    0.38
     sorriso
    0.38
     Prä
    0.38
    dunk
    0.37
    unk
    0.37
    Act Density 0.096%

    No Known Activations