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

    Neuronpedia

    INDEX
    Explanations

    namedtuple, TABLE, PDF, stakes, picks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     agribusiness
    0.59
    )
    0.55
     landscape
    0.55
    logic
    0.53
     perennial
    0.52
    ag
    0.51
    baru
    0.50
    hya
    0.49
     primary
    0.49
     life
    0.49
    POSITIVE LOGITS
    ა
    0.62
    ни
    0.55
    ة
    0.55
     genauso
    0.54
     degrades
    0.53
    <unused328>
    0.52
     فولت
    0.50
    ą
    0.50
    يات
    0.50
     电
    0.50
    Act Density 0.000%

    No Known Activations