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

    Neuronpedia

    INDEX
    Explanations

    addition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sky
    -0.07
     nearby
    -0.07
     milk
    -0.07
     experience
    -0.07
     share
    -0.07
     enduring
    -0.06
     seas
    -0.06
     Ikea
    -0.06
    Cow
    -0.06
     напря
    -0.06
    POSITIVE LOGITS
     addition
    0.09
     Addition
    0.07
     durum
    0.07
     besides
    0.06
     ΠΡ
    0.06
    -add
    0.06
    .subscriptions
    0.06
     �
    0.06
    -signed
    0.06
    .SelectedValue
    0.06
    Act Density 0.006%

    No Known Activations