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

    Neuronpedia

    INDEX
    Explanations

    Continuing sentences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ραση
    -0.06
     décor
    -0.06
    "text
    -0.06
     کیلومتر
    -0.06
     pouvez
    -0.06
     vyrob
    -0.06
    ณ
    -0.06
    _private
    -0.06
     Vault
    -0.06
    ้ใน
    -0.06
    POSITIVE LOGITS
    isman
    0.07
    bett
    0.06
     Rhino
    0.06
    EB
    0.06
    �
    0.06
     menacing
    0.06
     RCC
    0.06
    md
    0.06
    Prefab
    0.06
     Αλ
    0.06
    Act Density 0.003%

    No Known Activations