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

    Neuronpedia

    INDEX
    Explanations

    assisting nurses, refrigerated trailers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     compr
    0.40
     TYPES
    0.39
    اران
    0.38
     Rif
    0.37
     bundling
    0.37
     Comple
    0.37
    ራት
    0.36
     Straits
    0.36
     సంస్థ
    0.35
     ১৯৯
    0.35
    POSITIVE LOGITS
     jeopardy
    0.45
    (`#
    0.41
    möglich
    0.41
    瑰
    0.39
    ṯ
    0.38
    GAP
    0.38
     scoperta
    0.38
    CEA
    0.38
    Ng
    0.37
    TA
    0.37
    Act Density 0.000%

    No Known Activations