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

    Neuronpedia

    INDEX
    Explanations

    line/lines

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Burger
    -0.07
    吃过
    -0.07
    หาร
    -0.07
     lore
    -0.07
    xAF
    -0.06
    转移到
    -0.06
    经济损失
    -0.06
    億元
    -0.06
     COMPUTER
    -0.06
     bio
    -0.06
    POSITIVE LOGITS
    .Round
    0.07
    ivalent
    0.07
    Compact
    0.07
     einf
    0.06
    ぅ
    0.06
     cadastr
    0.06
    喱
    0.06
     RAID
    0.06
     Saturdays
    0.06
    Android
    0.06
    Act Density 0.013%

    No Known Activations