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

    Neuronpedia

    INDEX
    Explanations

    say "|" character

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    헙
    -0.07
    ᶰ
    -0.07
    ﲤ
    -0.07
    确
    -0.06
    ঔ
    -0.06
     한번
    -0.06
    �
    -0.06
    олж
    -0.06
     poc
    -0.06
     passe
    -0.06
    POSITIVE LOGITS
    (QObject
    0.08
    医疗
    0.07
    Square
    0.07
     pearls
    0.07
    (queue
    0.07
    addField
    0.07
    护肤
    0.07
     Larson
    0.07
    قوي
    0.07
    美容
    0.06
    Act Density 0.067%

    No Known Activations