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

    Neuronpedia

    INDEX
    Explanations

    detect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -schema
    -0.07
     Lock
    -0.07
    满意的
    -0.07
     peers
    -0.07
    _framework
    -0.07
    _CONV
    -0.07
     demons
    -0.07
    translated
    -0.07
     fetch
    -0.07
     assays
    -0.06
    POSITIVE LOGITS
    ichtig
    0.08
    _corner
    0.07
    져
    0.07
    몽
    0.07
    によ
    0.07
    失踪
    0.07
    _Session
    0.07
    ChartData
    0.07
    📼
    0.07
    строитель
    0.07
    Act Density 0.010%

    No Known Activations