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

    Neuronpedia

    INDEX
    Explanations

    resulting from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uccino
    0.48
     vanuit
    0.46
     sadrž
    0.44
     উৎপত্তি
    0.44
     unhappy
    0.43
    从
    0.42
    龊
    0.42
    Cindy
    0.41
    尘
    0.41
     giddy
    0.41
    POSITIVE LOGITS
    resulting
    0.57
     resulting
    0.56
    ultan
    0.40
     resultant
    0.39
     resulted
    0.37
     sult
    0.37
     complicating
    0.36
    ulta
    0.35
    स्टिव
    0.35
    CHO
    0.35
    Act Density 0.004%

    No Known Activations