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

    Neuronpedia

    INDEX
    Explanations

    regularization techniques and economic growth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ar
    0.91
    Effects
    0.88
    Questions
    0.87
    Nullable
    0.85
    ار
    0.84
    ia
    0.84
    在
    0.83
    由
    0.82
    出售
    0.80
    Emojis
    0.80
    POSITIVE LOGITS
    sas
    0.85
     supuesto
    0.81
     directamente
    0.78
     squint
    0.77
     dedicado
    0.75
    𝓲
    0.75
     sash
    0.73
    i
    0.72
     sink
    0.72
    𝘶
    0.72
    Act Density 0.000%

    No Known Activations