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

    Neuronpedia

    INDEX
    Explanations

    surgery

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    endDate
    -0.07
     NodeType
    -0.07
     две
    -0.07
     devlet
    -0.06
    ें↵↵
    -0.06
    '_
    -0.06
    ...\
    -0.06
    ̃
    -0.06
    улю
    -0.06
     των
    -0.06
    POSITIVE LOGITS
     Stripe
    0.06
     historical
    0.06
    closing
    0.06
     substit
    0.06
    skin
    0.06
     substitution
    0.06
     би
    0.06
    inputs
    0.06
     Utility
    0.06
    myModal
    0.06
    Act Density 0.059%

    No Known Activations