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

    Neuronpedia

    INDEX
    Explanations

    MP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Proto
    -0.07
     kul
    -0.07
     período
    -0.06
    sik
    -0.06
     грун
    -0.06
     دادن
    -0.06
     chaud
    -0.06
     guid
    -0.06
     fron
    -0.06
     BAŞ
    -0.06
    POSITIVE LOGITS
    ♀♀♀♀
    0.07
    Doctors
    0.07
    umbnails
    0.06
     dps
    0.06
     omp
    0.06
    omp
    0.06
    バー
    0.06
    letes
    0.06
    τές
    0.06
    '];↵
    0.06
    Act Density 0.000%

    No Known Activations