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

    Neuronpedia

    INDEX
    Explanations

    Go modules

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
     Mehmet
    -0.08
    ーカー
    -0.08
     Gemeinsam
    -0.08
    -connected
    -0.07
     Spielberg
    -0.07
     Ş
    -0.07
     Esq
    -0.07
     Meh
    -0.07
     izb
    -0.07
    POSITIVE LOGITS
     Modules
    0.12
     modules
    0.11
     go
    0.11
    Lang
    0.11
     módulos
    0.11
     gode
    0.11
    (lang
    0.11
     GOP
    0.11
     Go
    0.10
     গো
    0.10
    Act Density 0.005%

    No Known Activations