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

    Neuronpedia

    INDEX
    Explanations

    past tense indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     заре
    0.46
    แก้
    0.42
     ван
    0.42
    返
    0.41
     reintegr
    0.40
    Hopefully
    0.39
     remake
    0.39
    قر
    0.39
     பணிய
    0.39
     alleviated
    0.39
    POSITIVE LOGITS
    i
    0.48
     Sniper
    0.47
     tutaj
    0.45
     Cuff
    0.44
     Selon
    0.44
     Newspapers
    0.43
     aici
    0.43
     Holidays
    0.42
     hashCode
    0.42
     olduğuna
    0.42
    Act Density 0.002%

    No Known Activations