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

    Neuronpedia

    INDEX
    Explanations

    library

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Material
    -0.06
     NB
    -0.06
     settlements
    -0.06
     Wage
    -0.06
     bardzo
    -0.06
     indent
    -0.06
     territories
    -0.06
    ...'↵
    -0.06
     Straw
    -0.06
    есто
    -0.06
    POSITIVE LOGITS
    adding
    0.07
     rencont
    0.06
    右
    0.06
    いか
    0.06
     Telescope
    0.06
     (£
    0.06
    brief
    0.06
     (![
    0.06
     몽
    0.06
     getS
    0.06
    Act Density 0.007%

    No Known Activations