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

    Neuronpedia

    INDEX
    Explanations

    things and situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    に含ま
    0.88
    Lors
    0.80
    に使用
    0.80
    使用
    0.77
     ayrıca
    0.75
    行う
    0.74
     menghub
    0.74
     حين
    0.73
    際に
    0.72
    plicates
    0.72
    POSITIVE LOGITS
     things
    1.83
     Things
    1.72
    Things
    1.59
     THINGS
    1.59
    things
    1.46
     পরিস্থিতি
    1.33
     चीजें
    1.25
     cosas
    1.24
     పరిస్థి
    1.22
     momentum
    1.21
    Act Density 0.263%

    No Known Activations