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

    Neuronpedia

    INDEX
    Explanations

    ```terraform code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ו
    1.36
    აც
    1.13
    nama
    1.10
    ification
    1.09
    ie
    1.07
    nad
    1.04
    اف
    1.04
    ilda
    1.01
    iveness
    1.01
    ignment
    1.00
    POSITIVE LOGITS
     Ngoài
    1.25
    لكتر
    1.08
    Ngoài
    1.06
     வகுப்பு
    0.98
    ை
    0.97
    ைச்
    0.97
    ˆ‚
    0.97
    €”
    0.95
    soccer
    0.95
     تحتاج
    0.94
    Act Density 0.002%

    No Known Activations