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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FL
    -0.08
    decision
    -0.06
     personel
    -0.06
     Depend
    -0.06
    '",↵
    -0.06
    (pi
    -0.06
     Quentin
    -0.06
     smiling
    -0.06
    旅
    -0.06
     educator
    -0.06
    POSITIVE LOGITS
    ">*</
    0.07
     rand
    0.07
     कहन
    0.06
     เร
    0.06
     hel
    0.06
     TOD
    0.06
     rk
    0.06
     commod
    0.06
     sobě
    0.06
     jednot
    0.06
    Act Density 0.133%

    No Known Activations