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

    Neuronpedia

    INDEX
    Explanations

    Architectural and related professions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.49
    ター
    0.49
    ers
    0.43
     Neste
    0.43
    ب
    0.41
    bors
    0.41
    born
    0.40
     royaume
    0.40
    uert
    0.40
    ब्स
    0.40
    POSITIVE LOGITS
     Emeritus
    0.49
    lüğ
    0.47
     emeritus
    0.41
    ieken
    0.39
    ческое
    0.37
    ্ভব
    0.37
    ^+
    0.37
     ஒருவர்
    0.36
    schaft
    0.36
    qdm
    0.36
    Act Density 0.021%

    No Known Activations