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

    Neuronpedia

    INDEX
    Explanations

    Harmonized System codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sulfates
    0.39
    制造商
    0.38
     কংগ্রেস
    0.38
     VPS
    0.36
     Sandwich
    0.36
     subdued
    0.35
     CMV
    0.35
     factory
    0.35
     Schmidt
    0.35
     EI
    0.35
    POSITIVE LOGITS
    Air
    0.41
    Lim
    0.41
    Parsing
    0.39
    ith
    0.38
    Immun
    0.38
    Baba
    0.37
    Implemented
    0.37
     други
    0.37
    Ek
    0.37
    Bh
    0.37
    Act Density 0.002%

    No Known Activations