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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vp
    -0.07
    /welcome
    -0.06
     полов
    -0.06
     ActionTypes
    -0.06
     Más
    -0.06
    Devices
    -0.06
     dynasty
    -0.06
    フ
    -0.06
    .Cancel
    -0.06
     Buy
    -0.06
    POSITIVE LOGITS
    .ask
    0.07
    ersions
    0.07
    δια
    0.07
    ccb
    0.06
    _CONDITION
    0.06
     зберіг
    0.06
    建築
    0.06
     examined
    0.06
    計算
    0.06
    紹介
    0.06
    Act Density 0.010%

    No Known Activations