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

    Neuronpedia

    INDEX
    Explanations

    preparation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     explor
    -0.08
     Sentinel
    -0.08
    探索
    -0.08
     exploring
    -0.07
    危险
    -0.07
    全民
    -0.07
     Horde
    -0.07
     explored
    -0.07
    Subdivision
    -0.07
     convolution
    -0.07
    POSITIVE LOGITS
     vorbereitet
    0.13
     заранее
    0.13
    准备
    0.13
     preparada
    0.13
     준비
    0.12
     préparer
    0.12
     প্রস্তু
    0.12
     מראש
    0.12
     તૈય
    0.12
     preparedness
    0.12
    Act Density 0.045%

    No Known Activations