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

    Neuronpedia

    INDEX
    Explanations

    legal and government affairs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _date
    -0.07
     parte
    -0.07
    厌
    -0.07
     mostrar
    -0.07
    蒋
    -0.07
     wichtig
    -0.06
    tube
    -0.06
     hebben
    -0.06
    mat
    -0.06
    ],
    -0.06
    POSITIVE LOGITS
    骚扰
    0.07
    🏂
    0.07
    提高了
    0.07
     care
    0.07
    嵘
    0.06
    вший
    0.06
     uncommon
    0.06
     Daemon
    0.06
    猝
    0.06
     Erect
    0.06
    Act Density 0.100%

    No Known Activations