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

    Neuronpedia

    INDEX
    Explanations

    spa, geothermal, bath, vents, treatments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     somehow
    0.86
     cellulosic
    0.79
    ાર
    0.79
    lstm
    0.78
    گیری
    0.76
     bóng
    0.75
    an
    0.75
    %(
    0.74
    ′
    0.73
     loaf
    0.72
    POSITIVE LOGITS
    תה
    0.97
    už
    0.96
     शिल्पा
    0.91
     soaked
    0.90
     inad
    0.88
    უნქ
    0.87
    臾
    0.86
    ுக்
    0.86
     이는
    0.86
    țiile
    0.85
    Act Density 0.068%

    No Known Activations