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

    Neuronpedia

    INDEX
    Explanations

    verb followed by "it"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unor
    0.41
    Pada
    0.38
     unui
    0.38
     unei
    0.38
    こうした
    0.37
     asupra
    0.37
    على
    0.36
    في
    0.36
    出一个
    0.36
    دى
    0.35
    POSITIVE LOGITS
     it
    0.75
    它
    0.60
     它
    0.59
     nó
    0.56
    มัน
    0.52
     ĝi
    0.51
    it
    0.50
     It
    0.50
     इसे
    0.46
    它可以
    0.45
    Act Density 0.000%

    No Known Activations