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

    Neuronpedia

    INDEX
    Explanations

    modelOkay, starting responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Southeast
    0.37
    しまい
    0.36
    Oregon
    0.35
    ጕ
    0.33
    IM
    0.32
    œur
    0.32
    ORDON
    0.32
    жей
    0.31
    アン
    0.31
    Airbnb
    0.31
    POSITIVE LOGITS
     Examples
    0.38
     Lagi
    0.38
     Like
    0.38
     :)
    0.38
    ྵ
    0.38
     Além
    0.37
     подроб
    0.37
     Specify
    0.37
     macam
    0.37
     specify
    0.36
    Act Density 0.047%

    No Known Activations