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

    Neuronpedia

    INDEX
    Explanations

    data loading and adapters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ignon
    0.43
    midrule
    0.42
    рии
    0.41
     הב
    0.41
     sumo
    0.41
    텨
    0.40
     trophy
    0.39
    smaller
    0.39
     tiger
    0.38
    tool
    0.38
    POSITIVE LOGITS
    ArrayAdapter
    0.49
     Adapter
    0.46
     Adap
    0.46
     adapter
    0.45
    ListAdapter
    0.44
    adapter
    0.43
    TableAdapter
    0.42
     mile
    0.40
    アダ
    0.40
     ArrayAdapter
    0.40
    Act Density 0.098%

    No Known Activations