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

    Neuronpedia

    INDEX
    Explanations

    * explain what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TRY
    0.37
    Maybe
    0.36
     PUR
    0.36
    সাং
    0.36
    ظل
    0.36
    Julia
    0.35
    ܚ
    0.35
     X
    0.35
     Dire
    0.35
     जता
    0.34
    POSITIVE LOGITS
     Moines
    0.49
     Saunders
    0.44
    тории
    0.44
     dormitory
    0.42
     discharging
    0.40
    水源
    0.39
    ൂടെ
    0.39
    थिंग
    0.39
    थियों
    0.39
    ίας
    0.39
    Act Density 0.000%

    No Known Activations