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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Parad
    -0.07
     GetMessage
    -0.07
    badge
    -0.07
    MarshalAs
    -0.07
     flies
    -0.06
     Nhĩ
    -0.06
     obliged
    -0.06
    resses
    -0.06
     retour
    -0.06
     asc
    -0.06
    POSITIVE LOGITS
    vatel
    0.07
    leneck
    0.07
    persona
    0.07
    客
    0.06
     натураль
    0.06
     �
    0.06
    .Server
    0.06
     千
    0.06
    ailing
    0.06
    ailed
    0.06
    Act Density 0.001%

    No Known Activations