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

    Neuronpedia

    INDEX
    Explanations

    where, referring to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fant
    0.44
    นี
    0.40
     fantástico
    0.40
    茯
    0.39
     ovoj
    0.38
     carica
    0.38
    챙
    0.37
    생
    0.35
    竟然
    0.35
     Multif
    0.34
    POSITIVE LOGITS
     referring
    0.76
     Referring
    0.70
     wherein
    0.65
     refers
    0.64
    where
    0.62
     where
    0.61
     где
    0.59
    Referring
    0.59
    指的是
    0.57
     যেখানে
    0.57
    Act Density 0.443%

    No Known Activations