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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acija
    -0.07
    were
    -0.07
     Fuller
    -0.07
    inář
    -0.07
     slips
    -0.06
     بیماری
    -0.06
    ơn
    -0.06
    437
    -0.06
    把
    -0.06
     Governors
    -0.06
    POSITIVE LOGITS
     thinly
    0.07
     floated
    0.07
     Newsletter
    0.06
     morb
    0.06
    UnityEngine
    0.06
    .SERVER
    0.06
    urchases
    0.06
     chick
    0.06
     ヾ
    0.06
    グ
    0.06
    Act Density 0.005%

    No Known Activations