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

    Neuronpedia

    INDEX
    Explanations

    birth dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queuing
    0.39
     addicts
    0.38
     primitives
    0.38
    THER
    0.37
    品牌的
    0.37
     outcomes
    0.36
    supset
    0.35
    জু
    0.35
     "*.
    0.35
     rookies
    0.35
    POSITIVE LOGITS
     died
    0.59
     geboren
    0.54
     meninggal
    0.54
     nascita
    0.52
     murió
    0.49
    出生
    0.48
     muere
    0.47
     naissance
    0.47
     জন্মগ্রহণ
    0.47
    出身
    0.46
    Act Density 0.004%

    No Known Activations