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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    owel
    -0.07
    کا
    -0.07
     мус
    -0.06
    baum
    -0.06
     berg
    -0.06
    spent
    -0.06
    ократи
    -0.06
    593
    -0.06
     vers
    -0.06
    ova
    -0.06
    POSITIVE LOGITS
     Warrior
    0.06
     керів
    0.06
     zásad
    0.06
    ItemType
    0.06
    .predict
    0.06
    .unsubscribe
    0.06
    .categories
    0.06
     Mentor
    0.06
    Changed
    0.06
     []
↵
    0.06
    Act Density 0.080%

    No Known Activations