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

    Neuronpedia

    INDEX
    Explanations

    types of media

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hart
    -0.07
     SYNC
    -0.06
     DFA
    -0.06
    Tambah
    -0.06
    .flat
    -0.06
    ılış
    -0.06
    kud
    -0.05
    ayload
    -0.05
     SITE
    -0.05
     upgraded
    -0.05
    POSITIVE LOGITS
     possessions
    0.08
     trest
    0.07
     Dominican
    0.07
    urger
    0.07
    .setUsername
    0.07
     enthus
    0.07
     économ
    0.06
     punished
    0.06
    _
↵
    0.06
     TextEditingController
    0.06
    Act Density 0.043%

    No Known Activations