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

    Neuronpedia

    INDEX
    Explanations

    opening parentheses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _behavior
    -0.07
    oa
    -0.07
    ürlich
    -0.06
    ках
    -0.06
    Project
    -0.06
    جا
    -0.06
    small
    -0.06
     steam
    -0.06
    Police
    -0.06
     Rakou
    -0.06
    POSITIVE LOGITS
     đưa
    0.08
     تحميل
    0.07
    ты
    0.06
     oral
    0.06
     حضور
    0.06
     amplify
    0.06
     jedná
    0.06
    怀
    0.06
     účast
    0.06
     eg
    0.06
    Act Density 0.006%

    No Known Activations