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

    Neuronpedia

    INDEX
    Explanations

    Bed:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gods
    1.66
    ಯೇ
    1.66
     Đây
    1.59
     doodle
    1.59
     Electrode
    1.58
    不但
    1.56
     deities
    1.55
     underdog
    1.52
    রা
    1.50
     enchant
    1.50
    POSITIVE LOGITS
    est
    2.20
    se
    2.19
    あたり
    2.17
    ᄄ
    1.88
    était
    1.86
    ade
    1.84
    ridden
    1.82
    いま
    1.80
    ergewöhn
    1.80
    го
    1.79
    Act Density 0.004%

    No Known Activations