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

    Neuronpedia

    INDEX
    Explanations

    special character prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    竑
    0.37
     духо
    0.37
    ……”
    0.36
    ጴ
    0.35
    გრამ
    0.34
     shortfall
    0.34
    一方
    0.34
     অন্তর্
    0.34
    啼
    0.33
    苾
    0.33
    POSITIVE LOGITS
    help
    0.54
    info
    0.51
    thumb
    0.46
    heart
    0.45
    tea
    0.45
    love
    0.44
    flowers
    0.44
    tech
    0.44
    recycle
    0.43
    dev
    0.43
    Act Density 0.042%

    No Known Activations