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

    Neuronpedia

    INDEX
    Explanations

    list index out of range

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ilegal
    0.39
     Yucatán
    0.39
     bathroom
    0.36
     subtleties
    0.35
    বান
    0.35
    డ
    0.35
     illustrates
    0.35
     Zoning
    0.35
     branding
    0.34
    全市
    0.34
    POSITIVE LOGITS
    stethoscope
    0.39
     eher
    0.39
     लकार
    0.39
    萎
    0.38
     группа
    0.37
     potrzeb
    0.37
     Многие
    0.37
     sasane
    0.37
     JOH
    0.36
    탰
    0.36
    Act Density 0.002%

    No Known Activations