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

    Neuronpedia

    INDEX
    Explanations

    initiatives, programs, labs, or services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     presença
    0.69
    说什么
    0.66
    पीरियंस
    0.66
     आगमन
    0.65
     наличи
    0.64
     আলাপ
    0.63
     வணக்கம்
    0.62
     어떻게
    0.61
    動作
    0.60
     име
    0.60
    POSITIVE LOGITS
    ™
    1.53
    ™,
    1.39
     Initiative
    1.37
    ®
    1.34
    TM
    1.29
    ℠
    1.27
     ™
    1.27
    ™.
    1.20
     Project
    1.18
     initiative
    1.14
    Act Density 0.186%

    No Known Activations