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

    Neuronpedia

    INDEX
    Explanations

    preservation of data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     allowances
    -0.08
     bip
    -0.08
     allowance
    -0.08
     tub
    -0.08
     terminals
    -0.08
     rating
    -0.07
     permis
    -0.07
     ఇట
    -0.07
     moulin
    -0.07
     wild
    -0.07
    POSITIVE LOGITS
     immortal
    0.11
    保存
    0.11
     保存
    0.11
    存
    0.11
     संग्रह
    0.10
     收藏
    0.10
     永
    0.10
    .Save
    0.10
    永
    0.10
     permanence
    0.10
    Act Density 0.034%

    No Known Activations