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

    Neuronpedia

    INDEX
    Explanations

    lection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shield
    -0.07
    픕
    -0.07
    东京
    -0.07
     })↵↵
    -0.07
     Hole
    -0.07
    Delete
    -0.07
     TP
    -0.07
     solved
    -0.07
     ud
    -0.07
     Chip
    -0.07
    POSITIVE LOGITS
     contractor
    0.08
     bathrooms
    0.07
    строитель
    0.07
    loat
    0.07
     amalg
    0.07
     Yorkers
    0.07
     ünivers
    0.07
    陛
    0.07
     lesbian
    0.07
     involuntary
    0.07
    Act Density 0.004%

    No Known Activations