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

    Neuronpedia

    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hơn
    -0.07
    Tier
    -0.07
     beverage
    -0.07
    trx
    -0.07
    /win
    -0.06
     елем
    -0.06
     Grain
    -0.06
    ircon
    -0.06
    采购
    -0.06
    toa
    -0.06
    POSITIVE LOGITS
     ".
    0.07
    APON
    0.07
     Sy
    0.07
    (decimal
    0.06
     blows
    0.06
    语
    0.06
     '*
    0.06
    .title
    0.06
    nego
    0.06
    NZ
    0.06
    Act Density 0.033%

    No Known Activations