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

    Neuronpedia

    INDEX
    Explanations

    conversations and dialogues

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    initializer
    -0.08
    ctic
    -0.07
    酸
    -0.07
     recall
    -0.06
    (forKey
    -0.06
     Гри
    -0.06
     Stern
    -0.06
     꼭
    -0.06
     mice
    -0.06
    wendung
    -0.06
    POSITIVE LOGITS
    Unity
    0.07
     driv
    0.07
    ست
    0.06
     getTitle
    0.06
     Unity
    0.06
    Gold
    0.06
     SRC
    0.06
     ullam
    0.06
     Garten
    0.06
     Yönetim
    0.05
    Act Density 0.114%

    No Known Activations