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

    Neuronpedia

    INDEX
    Explanations

    comparison and alignment with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Trans
    0.36
    듀
    0.36
     Cand
    0.36
     التعامل
    0.36
     ভি
    0.35
    ks
    0.35
     Career
    0.35
     With
    0.34
     Delta
    0.34
     Contact
    0.34
    POSITIVE LOGITS
    กับการ
    0.86
     closely
    0.70
     seamlessly
    0.66
     miteinander
    0.61
    与其他
    0.61
    กับ
    0.61
     favorably
    0.61
     favourably
    0.56
    与
    0.54
    ກັບ
    0.54
    Act Density 0.092%

    No Known Activations