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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (bg
    -0.07
    _VENDOR
    -0.07
    svc
    -0.06
     Kylie
    -0.06
     emulate
    -0.06
    /")↵
    -0.06
    _SC
    -0.06
     cors
    -0.06
    enez
    -0.06
    .Services
    -0.06
    POSITIVE LOGITS
    основ
    0.06
     fisheries
    0.06
    Leo
    0.06
     gentle
    0.06
     Uygu
    0.06
     educating
    0.06
     faithful
    0.06
     Thanh
    0.05
     legend
    0.05
     milan
    0.05
    Act Density 0.008%

    No Known Activations