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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     indict
    -0.06
     mango
    -0.06
     Clothes
    -0.06
     App
    -0.06
    bruary
    -0.06
    一
    -0.06
     rat
    -0.06
    haven
    -0.06
     mít
    -0.06
    �ng
    -0.06
    POSITIVE LOGITS
    MemoryWarning
    0.07
     Созд
    0.07
    Accessory
    0.06
     �
    0.06
     gereken
    0.06
    DEFINE
    0.06
     =="
    0.06
     Wash
    0.06
    .vue
    0.06
     toplum
    0.06
    Act Density 0.006%

    No Known Activations